Skip to content

This content can't be shown We take extra caution with cybersecurity requests. #34306

Open

Description

@Recodify

What version of Codex CLI is running?

codex-cli 0.144.6

What subscription do you have?

pro

Which model were you using?

gpt-5.6-sol-xhigh

What platform is your computer?

#Linux 6.17.0-23-generic x86_64 x86_64

What terminal emulator and version are you using (if applicable)?

gnomeTerminal/bash

Codex doctor report

{
  "schemaVersion": 1,
  "generatedAt": "1784538830s since unix epoch",
  "overallStatus": "warning",
  "codexVersion": "0.144.6",
  "checks": {
    "app_server.status": {
      "id": "app_server.status",
      "category": "app-server",
      "status": "ok",
      "summary": "background server is not running",
      "details": {
        "control socket": "/home/sam/.codex/app-server-control/app-server-control.sock",
        "daemon state dir": "/home/sam/.codex/app-server-daemon",
        "mode": "ephemeral",
        "pid file": "/home/sam/.codex/app-server-daemon/app-server.pid (missing)",
        "settings": "/home/sam/.codex/app-server-daemon/settings.json (missing)",
        "status": "not running",
        "update-loop pid file": "/home/sam/.codex/app-server-daemon/app-server-updater.pid (missing)"
      },
      "remediation": null,
      "durationMs": 0
    },
    "auth.credentials": {
      "id": "auth.credentials",
      "category": "auth",
      "status": "ok",
      "summary": "auth is configured",
      "details": {
        "auth file": "/home/sam/.codex/auth.json",
        "auth storage mode": "File",
        "stored API key": "false",
        "stored ChatGPT tokens": "true",
        "stored agent identity": "false",
        "stored auth mode": "chatgpt"
      },
      "remediation": null,
      "durationMs": 0
    },
    "config.load": {
      "id": "config.load",
      "category": "config",
      "status": "ok",
      "summary": "config loaded",
      "details": {
        "CODEX_HOME": "/home/sam/.codex",
        "config.toml": "/home/sam/.codex/config.toml",
        "config.toml parse": "ok",
        "cwd": "/home/sam/code/ClickHouse",
        "enabled feature flags": "shell_tool, unified_exec, shell_snapshot, code_mode_host, terminal_resize_reflow, sqlite, hooks, enable_request_compression, multi_agent, apps, tool_search_always_defer_mcp_tools, tool_suggest, plugins, in_app_browser, browser_use, browser_use_full_cdp_access, browser_use_external, computer_use, remote_plugin, plugin_sharing, image_generation, resize_all_images, skill_mcp_dependency_install, mentions_v2, steer, guardian_approval, goals, collaboration_modes, tool_call_mcp_elicitation, auth_elicitation, personality, fast_mode, tui_app_server, remote_compaction_v2, workspace_dependencies",
        "feature flag overrides": "none",
        "feature flags enabled": "35",
        "log dir": "/home/sam/.codex/log",
        "mcp servers": "1",
        "model": "gpt-5.6-sol",
        "model provider": "openai",
        "sqlite home": "/home/sam/.codex"
      },
      "remediation": null,
      "durationMs": 0
    },
    "git.environment": {
      "id": "git.environment",
      "category": "git",
      "status": "ok",
      "summary": "git version 2.43.0",
      "details": {
        ".git entry": "directory",
        "PATH git #1": "/usr/bin/git",
        "PATH git #2": "/bin/git",
        "PATH git entries": "2",
        "git branch": "schema-visualizer-web-ui",
        "git build options": "git version 2.43.0; cpu: x86_64; no commit associated with this build; sizeof-long: 8; sizeof-size_t: 8; shell-path: /bin/sh",
        "git exec path": "/usr/lib/git-core",
        "git version": "git version 2.43.0",
        "repo detected": "true",
        "repo root": "/home/sam/code/ClickHouse",
        "selected git": "/usr/bin/git"
      },
      "remediation": null,
      "durationMs": 29
    },
    "installation": {
      "id": "installation",
      "category": "install",
      "status": "ok",
      "summary": "installation looks consistent",
      "details": {
        "PATH codex #1": "/home/sam/.nvm/versions/node/v24.14.1/bin/codex",
        "PATH codex #2": "/usr/local/bin/codex",
        "PATH codex entries": "2",
        "current executable": "/home/sam/.nvm/versions/node/v24.14.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/bin/codex",
        "install context": "npm (package /home/sam/.nvm/versions/node/v24.14.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl, bin /home/sam/.nvm/versions/node/v24.14.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/bin, resources /home/sam/.nvm/versions/node/v24.14.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/codex-resources, path /home/sam/.nvm/versions/node/v24.14.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/codex-path)",
        "managed by bun": "false",
        "managed by npm": "true",
        "managed by pnpm": "false",
        "managed package root": "/home/sam/.nvm/versions/node/v24.14.1/lib/node_modules/@openai/codex",
        "npm update target": "/home/sam/.nvm/versions/node/v24.14.1/lib/node_modules/@openai/codex"
      },
      "remediation": null,
      "durationMs": 70
    },
    "mcp.config": {
      "id": "mcp.config",
      "category": "mcp",
      "status": "ok",
      "summary": "MCP configuration is locally consistent",
      "details": {
        "configured servers": "1",
        "disabled servers": "0",
        "streamable_http servers": "1"
      },
      "remediation": null,
      "durationMs": 3301
    },
    "network.env": {
      "id": "network.env",
      "category": "network",
      "status": "ok",
      "summary": "network-related environment looks readable",
      "details": {
        "proxy env vars": "none"
      },
      "remediation": null,
      "durationMs": 0
    },
    "network.provider_reachability": {
      "id": "network.provider_reachability",
      "category": "reachability",
      "status": "ok",
      "summary": "active provider endpoints are reachable over HTTP",
      "details": {
        "ChatGPT base URL": "https://chatgpt.com/backend-api/ reachable (HTTP 404)",
        "reachability mode": "ChatGPT auth"
      },
      "remediation": null,
      "durationMs": 871
    },
    "network.websocket_reachability": {
      "id": "network.websocket_reachability",
      "category": "websocket",
      "status": "ok",
      "summary": "Responses WebSocket handshake succeeded",
      "details": {
        "DNS": "2 IPv4, 2 IPv6, first IPv4",
        "auth mode": "chatgpt",
        "connect timeout": "15000 ms",
        "endpoint": "wss://chatgpt.com/backend-api/<redacted>",
        "handshake result": "HTTP 101 Switching Protocols",
        "model provider": "openai",
        "models etag present": "true",
        "provider name": "OpenAI",
        "proxy env vars": "none",
        "reasoning header": "false",
        "server model present": "false",
        "supports websockets": "true",
        "wire API": "responses"
      },
      "remediation": null,
      "durationMs": 645
    },
    "runtime.provenance": {
      "id": "runtime.provenance",
      "category": "runtime",
      "status": "ok",
      "summary": "running npm on linux-x86_64",
      "details": {
        "commit": "unknown",
        "current executable": "/home/sam/.nvm/versions/node/v24.14.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/bin/codex",
        "install method": "npm (package /home/sam/.nvm/versions/node/v24.14.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl, bin /home/sam/.nvm/versions/node/v24.14.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/bin, resources /home/sam/.nvm/versions/node/v24.14.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/codex-resources, path /home/sam/.nvm/versions/node/v24.14.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/codex-path)",
        "platform": "linux-x86_64",
        "version": "0.144.6"
      },
      "remediation": null,
      "durationMs": 0
    },
    "runtime.search": {
      "id": "runtime.search",
      "category": "search",
      "status": "ok",
      "summary": "search is OK (bundled)",
      "details": {
        "search command": "/home/sam/.nvm/versions/node/v24.14.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/codex-path/rg",
        "search command readiness": "file exists",
        "search provider": "bundled"
      },
      "remediation": null,
      "durationMs": 0
    },
    "sandbox.helpers": {
      "id": "sandbox.helpers",
      "category": "sandbox",
      "status": "ok",
      "summary": "sandbox configuration is readable",
      "details": {
        "approval policy": "OnRequest",
        "codex-linux-sandbox helper": "/home/sam/.codex/tmp/arg0/codex-arg0Nyq0Sg/codex-linux-sandbox",
        "execve wrapper helper": "/home/sam/.codex/tmp/arg0/codex-arg0Nyq0Sg/codex-execve-wrapper",
        "filesystem sandbox": "unrestricted",
        "network sandbox": "enabled"
      },
      "remediation": null,
      "durationMs": 0
    },
    "state.paths": {
      "id": "state.paths",
      "category": "state",
      "status": "ok",
      "summary": "state paths and databases are inspectable",
      "details": {
        "CODEX_HOME": "/home/sam/.codex (dir)",
        "active rollout files": "381 files, 1100372503 total bytes, 2888116 average bytes",
        "archived rollout files": "0 files, 0 total bytes, 0 average bytes",
        "goals DB": "/home/sam/.codex/goals_1.sqlite (file)",
        "goals DB integrity": "ok",
        "log DB": "/home/sam/.codex/logs_2.sqlite (file)",
        "log DB integrity": "ok",
        "log dir": "/home/sam/.codex/log (dir)",
        "memories DB": "/home/sam/.codex/memories_1.sqlite (file)",
        "memories DB integrity": "ok",
        "sqlite home": "/home/sam/.codex (dir)",
        "state DB": "/home/sam/.codex/state_5.sqlite (file)",
        "state DB integrity": "ok"
      },
      "remediation": null,
      "durationMs": 385
    },
    "state.rollout_db_parity": {
      "id": "state.rollout_db_parity",
      "category": "threads",
      "status": "warning",
      "summary": "rollout files and state DB thread inventory differ",
      "details": {
        "default model provider": "openai",
        "rollout DB active files": "381",
        "rollout DB active rows": "379",
        "rollout DB archive mismatches": "0",
        "rollout DB archived files": "0",
        "rollout DB archived rows": "0",
        "rollout DB duplicate DB paths": "0",
        "rollout DB duplicate rollout thread ids": "0",
        "rollout DB malformed file names": "0",
        "rollout DB missing active rows": "2",
        "rollout DB missing active sample": [
          "/home/sam/.codex/sessions/2026/03/28/rollout-2026-03-28T00-59-40-019d31f4-341c-7fd2-a8b0-f6573418a18e.jsonl",
          "/home/sam/.codex/sessions/2026/03/28/rollout-2026-03-28T01-01-14-019d31f5-a181-7f02-9a99-bceab3f1f62a.jsonl"
        ],
        "rollout DB missing archived rows": "0",
        "rollout DB model providers": "openai=379",
        "rollout DB rows": "379",
        "rollout DB scan cap reached": "false",
        "rollout DB scan errors": "0",
        "rollout DB sources": "cli=270, vscode=107, subagent:thread_spawn=2",
        "rollout DB stale rows": "0"
      },
      "issues": [
        {
          "severity": "warning",
          "cause": "rollout files are missing from the state DB",
          "measured": "2 active, 0 archived",
          "expected": "every rollout file has a matching threads row",
          "remedy": null,
          "fields": []
        }
      ],
      "remediation": null,
      "durationMs": 8100
    },
    "system.environment": {
      "id": "system.environment",
      "category": "system",
      "status": "ok",
      "summary": "OS language en-US",
      "details": {
        "EDITOR": "set",
        "LANG": "en_US.UTF-8",
        "VISUAL": "set",
        "os": "Ubuntu 24.4.0 (noble) [64-bit]",
        "os language": "en-US",
        "os type": "Ubuntu",
        "os version": "24.4.0"
      },
      "remediation": null,
      "durationMs": 5
    },
    "terminal.env": {
      "id": "terminal.env",
      "category": "terminal",
      "status": "ok",
      "summary": "terminal metadata was detected",
      "details": {
        "COLORTERM": "truecolor",
        "DISPLAY": "present",
        "color output": "enabled",
        "effective locale": "en_US.UTF-8",
        "stderr is terminal": "true",
        "stdin is terminal": "true",
        "stdout is terminal": "true",
        "terminal": "GNOME Terminal",
        "terminal size": "144x72"
      },
      "remediation": null,
      "durationMs": 0
    },
    "terminal.title": {
      "id": "terminal.title",
      "category": "title",
      "status": "ok",
      "summary": "terminal title default",
      "details": {
        "terminal title activity": "true",
        "terminal title items": "activity, project-name",
        "terminal title project source": "git repo root",
        "terminal title project value": "ClickHouse",
        "terminal title source": "default"
      },
      "remediation": null,
      "durationMs": 0
    },
    "updates.status": {
      "id": "updates.status",
      "category": "updates",
      "status": "ok",
      "summary": "update configuration is locally consistent",
      "details": {
        "cached latest version": "0.144.6",
        "check for update on startup": "true",
        "dismissed version": "0.144.4",
        "last checked at": "2026-07-19T18:19:01.826726566Z",
        "latest version": "0.144.6",
        "latest version status": "current version is not older",
        "npm update target": "/home/sam/.nvm/versions/node/v24.14.1/lib/node_modules/@openai/codex",
        "update action": "npm install -g @openai/codex",
        "version cache": "/home/sam/.codex/version.json"
      },
      "remediation": null,
      "durationMs": 764
    }
  }
}

What issue are you seeing?

ⓘ This content can't be shown
We take extra caution with cybersecurity requests. If you’re a security professional, you may be able to apply for Trusted Access.
Trusted Access: https://openai.com/form/enterprise-trusted-access-for-cyber/
Learn more: https://help.openai.com/en/articles/20001326

What steps can reproduce the bug?

Uploaded thread: 019f7cdd-aabd-78b2-a33c-f087d332f807

What is the expected behavior?

Doesn't trigger safeguards

Additional information

No response

Activity

  1. added
    CLIIssues related to the Codex CLI
    safety-checkIssues related to safety and abuse checks
    on Jul 20, 2026
  2. Recodify commented on Jul 20, 2026

    @Recodify
    Author

    Additionally, I'm also getting issues with other sessions displaying:

      Additional safety checks                                                                                                                    
      This request requires additional safety checks, which can take extra time. Hang tight or retry with a faster model for a quicker response,
      though it may be less capable of handling complex requests.
     
    › 1. Retry with a faster model
      2. Keep waiting
      3. Learn more
    

    e.g. thread ID 019f7ec0-fbe2-7ad1-8902-ff4fb2e8c6a1

  3. analytically commented on Jul 24, 2026

    @analytically

    Blocked by this. OpenAI do better

  4. cjmanca commented on Jul 24, 2026

    @cjmanca

    Seriously. Keeps popping up while I'm attempting to debug my own app. Very frustrating.

  5. dumebi042 commented on Jul 26, 2026

    @dumebi042

    Its worse today, can't do anything

  6. gsovereignty commented on Jul 28, 2026

    @gsovereignty

    Solved the problem by switching to GLM5.2 which is far less communist than this garbage.

  7. Gh0stlyKn1ght commented on Jul 31, 2026

    @Gh0stlyKn1ght

    I thought I was going crazy...

  8. fullofcaffeine commented on Jul 31, 2026

    @fullofcaffeine

    This is so annoying. What the f*** does this even mean?

  9. rommyarb commented on Aug 5, 2026

    @rommyarb

    WHAT THE FUCK, CODEX? I WAST JUST TRYING TO ACCESS MY GITLAB REPO with glab

  10. kappa9999 commented on Aug 7, 2026

    @kappa9999

    Additional compaction-specific reproduction (privacy-redacted)

    • Codex CLI: 0.147.0 on Windows 11 and Ubuntu under WSL; both installations resolve to @openai/codex 0.147.0.
    • Auth/model: ChatGPT sign-in; GPT-5.6 Sol with maximum reasoning.
    • Trusted Access: the account is already approved for Trusted Access for Cyber.
    • Local health: installation, login, provider reachability, and WebSocket diagnostics pass.
    • Reproduction: automatic context compaction completes successfully, then the benign non-cyber continuation receives the same cyber_policy block described in this issue. The failure is specifically correlated with the compaction/post-compaction boundary.
    • The affected work did not request malware, credential theft, destructive actions, persistence, evasion, or exploitation.

    For privacy, no session, thread, turn, request, or rollout identifiers; transcripts; prompt excerpts; exact event timestamps; local paths; or session-file contents will be provided.

    Could the team please check:

    1. Whether Trusted Access entitlement is propagated to remote compaction and the first post-compaction request.
    2. Whether compacted context can lose the benign/authorized framing and cause a false-positive safety reclassification.
    3. Whether the backend can expose a stable, privacy-preserving safety failure reference that Support can inspect without users disclosing conversation identifiers.

    Potentially relevant but not confirmed causal: #37345 adds model-routing hints to normal Responses, remote-compaction, and WebSocket requests; that change is on main but is not in the rust-v0.147.0 tag.

  11. ThameeraDananjaya commented on Aug 8, 2026

    @ThameeraDananjaya

    Really frustrated, I'm just a freelancer and trying to build a Hospitality application. Build the security feature using Claude and asked GPT (Codex) to review the code and verify assuming it's reasoning for security context is more mature. Untimately the same trust identified me as a security risk. Funny..
    Chatted with OpenAI Chat bot Widget for hours to get a solution and finally sent an email to support@openai.com and the same AI bot responded to me with the same instructions. Funny..
    We are in 21st century and talk about how AI makes life better. The same AI plans the development scope instructing developers to deploy and AI agent with the application to get imediate alerts if critical work-flow is damaged or interrupted, then the same company owning the AI model says a real human will contact me after few days. Funny..
    So, I had to stop my work until the AI contact a real human and the human get back to me. Funny..

  12. mmphego commented on Aug 11, 2026

    @mmphego

    This is really frustrating, my prompt is very simple to say the least but I constantly get the popup:

    Review this repository for correctness and reliability.
    
    Use several independent reviewers to inspect different parts of the codebase. First understand the repository structure, then divide the main modules or subsystems between the reviewers.
    
    Each reviewer should focus on normal software engineering concerns such as:
    
    - Logic that may produce incorrect results
    - Unexpected behaviour for unusual inputs
    - Incorrect assumptions between components
    - Error handling problems
    - Async or concurrency mistakes
    - Data consistency issues
    - Configuration problems
    - Resource lifecycle problems
    - Gaps between implementation and tests
    
    Reviewers should follow important execution paths across files rather than only reading individual files.
    
    Do not change the implementation yet.
    
    For each issue found, provide:
    
    - File and function
    - What the code currently does
    - Why that behaviour may be incorrect
    - Conditions where it occurs
    - Expected behaviour
    - A suggested correction
    - A test that would validate the correction
    
    After the reviewers finish, use one additional reviewer to compare the findings, remove duplicates, and challenge questionable conclusions.
    
    Only keep findings that are supported by the code.
    
    Ignore formatting, naming, stylistic preferences, and optional refactoring unless they directly affect behaviour.
    
    At the end provide:
    
    1. Most important correctness issues
    2. Other confirmed issues
    3. Areas reviewed without notable issues
    4. Areas where additional tests would provide more confidence
    
    Do not make changes until the review is complete.
    
  13. pankajjpandeywork commented on Aug 11, 2026

    @pankajjpandeywork

    Any fix for this?

  14. Huasushis commented on Aug 15, 2026

    @Huasushis

    Same problem. codex-cli 0.147.0 with my thread ID 019fbca7-5d94-7412-af1c-915fac803d73

  15. pilotcolin commented on Aug 17, 2026

    @pilotcolin

    Same issue. building a finance tool (local to my pc) and not being able to see content.

  16. XxTheJanit0rxX commented on Aug 18, 2026

    @XxTheJanit0rxX

    Solved the problem by switching to GLM5.2 which is far less communist than this garbage.

    I'll do the same both openai and anthropic must be getting locked down by US Sanctions on AI and cybersecurity. I'll roll over to GLM as well this weekend. And Cancel one of the two I'm thinking both if GLM works out for my needs

  17. YKDZ commented on Aug 22, 2026

    @YKDZ

    I understand why Codex applies additional checks to cybersecurity-related requests, but this creates a chicken-and-egg problem: developers need to simulate adversarial inputs to verify that their own applications are secure, yet that simulation itself can easily be classified as attack-related behavior.

    My concrete case was very ordinary: I was using Codex to write Vitest tests for my own application, simulating invalid or malicious inputs against a signature verification feature to make sure the verification logic could not be bypassed. This was local, authorized, defensive unit testing. It did not involve any third-party target or real-world attack.

    However, once the current session is flagged this way, continuing unrelated normal development work also becomes difficult. In practice, the best workaround is to start a new Codex session and explicitly tell the agent not to touch that test implementation again.

    I hope Codex can handle this class of work more clearly: local repository, user-owned code, and defensive tests of security-sensitive logic, without making the entire session difficult to continue using.

  18. dezmen3 commented on Aug 25, 2026

    @dezmen3

    Usually happens like 1-2 times a month, now it's like 20 already for few hours, just a mmorpg server/client testing..

  19. dare-to-recurse commented on Sep 9, 2026

    @dare-to-recurse

    Same issue while trying to get GPT-6 to investigate a crash found in a differential fuzzing test comparing two different floating point parser implementations.

    Thread id: 01a07cb2-c2a3-7741-b2bf-b905fbb0b87f

  20. wegfawefgawefg commented on Sep 9, 2026

    @wegfawefgawefg

    Additional affected session uploaded through /feedback: 01a03c18-cfa2-7962-a266-e0b3031957a0.

    This reproduced repeatedly in Codex CLI with GPT-5.6 Sol High on Linux during authorized debugging of our own Rust financial application. The blocked work involved analyzing compiler/sanitizer output and testing deterministic event sequences for deadlocks and invalid state transitions. It did not involve a third-party target, credential access, persistence, evasion, or data exfiltration.

    The same workflow worked substantially more reliably before the Astra release; since then, the cybersecurity banner has appeared repeatedly over several days.

  21. Mohamed3bdelwahab commented on Sep 18, 2026

    @Mohamed3bdelwahab

    the same fucking issue , Same issue here on the Pro plan. It keeps getting falsely flagged for cybersecurity safety, leading to multi-day account lockouts during routine tasks. What is going on with these false positives, and when can we expect a fix?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    CLIIssues related to the Codex CLIbugSomething isn't workingsafety-checkIssues related to safety and abuse checks

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions