False positive of cybersecurity block for local adversarial machine learning research
Open 💬 1 comment Opened Jul 17, 2026 by yhli-ml
What version of Codex CLI is running?
codex-cli 0.144.5
What subscription do you have?
pro
Which model were you using?
gpt-5.6-sol
What platform is your computer?
Linux 5.15.0-181-generic x86_64 x86_64
What terminal emulator and version are you using (if applicable)?
Terminal.app
Codex doctor report
{
"schemaVersion": 1,
"generatedAt": "1784270263s since unix epoch",
"overallStatus": "warning",
"codexVersion": "0.144.5",
"checks": {
"app_server.status": {
"id": "app_server.status",
"category": "app-server",
"status": "warning",
"summary": "background server socket is stale or unreachable",
"details": {
"app-server version": "unavailable (failed to connect to control socket)",
"control socket": "/home/mila/j/jerry.huang/.codex/app-server-control/app-server-control.sock",
"daemon state dir": "/home/mila/j/jerry.huang/.codex/app-server-daemon",
"mode": "persistent",
"pid file": "/home/mila/j/jerry.huang/.codex/app-server-daemon/app-server.pid (file)",
"settings": "/home/mila/j/jerry.huang/.codex/app-server-daemon/settings.json (file)",
"status": "stale or unreachable",
"update-loop pid file": "/home/mila/j/jerry.huang/.codex/app-server-daemon/app-server-updater.pid (file)"
},
"remediation": "Run codex app-server daemon version for more details.",
"durationMs": 0
},
"auth.credentials": {
"id": "auth.credentials",
"category": "auth",
"status": "ok",
"summary": "auth is configured",
"details": {
"auth file": "/home/mila/j/jerry.huang/.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/mila/j/jerry.huang/.codex",
"config.toml": "/home/mila/j/jerry.huang/.codex/config.toml",
"config.toml parse": "ok",
"cwd": "/home/mila/j/jerry.huang",
"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/mila/j/jerry.huang/.codex/log",
"mcp servers": "0",
"model": "gpt-5.6-sol",
"model provider": "openai",
"sqlite home": "/home/mila/j/jerry.huang/.codex"
},
"remediation": null,
"durationMs": 0
},
"git.environment": {
"id": "git.environment",
"category": "git",
"status": "ok",
"summary": "git version 2.34.1",
"details": {
".git entry": "directory",
"PATH git #1": "/usr/bin/git",
"PATH git #2": "/bin/git",
"PATH git entries": "2",
"git build options": "git version 2.34.1; 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 2.34.1",
"repo detected": "true",
"repo root": "/home/mila/j/jerry.huang",
"selected git": "/usr/bin/git"
},
"remediation": null,
"durationMs": 139
},
"installation": {
"id": "installation",
"category": "install",
"status": "ok",
"summary": "installation looks consistent",
"details": {
"PATH codex #1": "/home/mila/j/jerry.huang/.local/bin/codex",
"PATH codex #2": "/home/mila/j/jerry.huang/.local/bin/codex",
"PATH codex #3": "/home/mila/j/jerry.huang/.nvm/versions/node/v24.15.0/bin/codex",
"PATH codex entries": "3",
"current executable": "/home/mila/j/jerry.huang/.codex/packages/standalone/releases/0.144.5-x86_64-unknown-linux-musl/bin/codex",
"install context": "standalone (unix, package /home/mila/j/jerry.huang/.codex/packages/standalone/releases/0.144.5-x86_64-unknown-linux-musl, bin /home/mila/j/jerry.huang/.codex/packages/standalone/releases/0.144.5-x86_64-unknown-linux-musl/bin, resources /home/mila/j/jerry.huang/.codex/packages/standalone/releases/0.144.5-x86_64-unknown-linux-musl/codex-resources, path /home/mila/j/jerry.huang/.codex/packages/standalone/releases/0.144.5-x86_64-unknown-linux-musl/codex-path)",
"managed by bun": "false",
"managed by npm": "false",
"managed by pnpm": "false",
"managed package root": "not set"
},
"remediation": null,
"durationMs": 6
},
"mcp.config": {
"id": "mcp.config",
"category": "mcp",
"status": "ok",
"summary": "no MCP servers configured",
"details": {},
"remediation": null,
"durationMs": 0
},
"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 403)",
"reachability mode": "ChatGPT auth"
},
"remediation": null,
"durationMs": 152
},
"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": 741
},
"runtime.provenance": {
"id": "runtime.provenance",
"category": "runtime",
"status": "ok",
"summary": "running standalone on linux-x86_64",
"details": {
"commit": "unknown",
"current executable": "/home/mila/j/jerry.huang/.codex/packages/standalone/releases/0.144.5-x86_64-unknown-linux-musl/bin/codex",
"install method": "standalone (unix, package /home/mila/j/jerry.huang/.codex/packages/standalone/releases/0.144.5-x86_64-unknown-linux-musl, bin /home/mila/j/jerry.huang/.codex/packages/standalone/releases/0.144.5-x86_64-unknown-linux-musl/bin, resources /home/mila/j/jerry.huang/.codex/packages/standalone/releases/0.144.5-x86_64-unknown-linux-musl/codex-resources, path /home/mila/j/jerry.huang/.codex/packages/standalone/releases/0.144.5-x86_64-unknown-linux-musl/codex-path)",
"platform": "linux-x86_64",
"version": "0.144.5"
},
"remediation": null,
"durationMs": 0
},
"runtime.search": {
"id": "runtime.search",
"category": "search",
"status": "ok",
"summary": "search is OK (bundled)",
"details": {
"search command": "/home/mila/j/jerry.huang/.codex/packages/standalone/releases/0.144.5-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": "Never",
"codex-linux-sandbox helper": "/home/mila/j/jerry.huang/.codex/tmp/arg0/codex-arg0vffiqB/codex-linux-sandbox",
"execve wrapper helper": "/home/mila/j/jerry.huang/.codex/tmp/arg0/codex-arg0vffiqB/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/mila/j/jerry.huang/.codex (dir)",
"active rollout files": "55 files, 859381337 total bytes, 15625115 average bytes",
"archived rollout files": "0 files, 0 total bytes, 0 average bytes",
"goals DB": "/home/mila/j/jerry.huang/.codex/goals_1.sqlite (file)",
"goals DB integrity": "ok",
"log DB": "/home/mila/j/jerry.huang/.codex/logs_2.sqlite (file)",
"log DB integrity": "ok",
"log dir": "/home/mila/j/jerry.huang/.codex/log (dir)",
"memories DB": "/home/mila/j/jerry.huang/.codex/memories_1.sqlite (file)",
"memories DB integrity": "ok",
"sqlite home": "/home/mila/j/jerry.huang/.codex (dir)",
"standalone release cache": "2 entries in /home/mila/j/jerry.huang/.codex/packages/standalone/releases",
"state DB": "/home/mila/j/jerry.huang/.codex/state_5.sqlite (file)",
"state DB integrity": "ok"
},
"remediation": null,
"durationMs": 1059
},
"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": "54",
"rollout DB active rows": "54",
"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": "0",
"rollout DB missing archived rows": "0",
"rollout DB model providers": "openai=54",
"rollout DB rows": "54",
"rollout DB scan cap reached": "false",
"rollout DB scan error sample": "/home/mila/j/jerry.huang/.codex/sessions/2026/05/24/rollout-2026-05-24T12-40-27-019e5adb-fc8b-7d30-942e-de6c2e47198f.jsonl (empty session file)",
"rollout DB scan errors": "1",
"rollout DB sources": "subagent:thread_spawn=24, cli=15, vscode=13, exec=2",
"rollout DB stale rows": "0"
},
"issues": [
{
"severity": "warning",
"cause": "rollout scan was incomplete or found bad files",
"measured": "1 scan errors, 0 malformed names, scan cap reached: false",
"expected": "rollout directories are fully scannable",
"remedy": "Check file permissions and unexpected files under CODEX_HOME sessions.",
"fields": []
}
],
"remediation": null,
"durationMs": 7493
},
"system.environment": {
"id": "system.environment",
"category": "system",
"status": "ok",
"summary": "OS language C",
"details": {
"EDITOR": "not set",
"LANG": "C.UTF-8",
"LC_CTYPE": "C.UTF-8",
"VISUAL": "not set",
"os": "Ubuntu 22.4.0 (jammy) [64-bit]",
"os language": "C",
"os type": "Ubuntu",
"os version": "22.4.0"
},
"remediation": null,
"durationMs": 87
},
"terminal.env": {
"id": "terminal.env",
"category": "terminal",
"status": "ok",
"summary": "terminal metadata was detected",
"details": {
"SSH_CLIENT": "present",
"SSH_CONNECTION": "present",
"SSH_TTY": "present",
"TERM": "xterm-256color",
"color output": "enabled",
"effective locale": "C.UTF-8",
"stderr is terminal": "true",
"stdin is terminal": "true",
"stdout is terminal": "true",
"terminal": "unknown",
"terminal size": "360x86"
},
"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": "jerry.huang",
"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": "0.144.5",
"check for update on startup": "true",
"last checked at": "2026-07-17T01:17:44.146927684Z",
"latest version": "0.144.5",
"latest version status": "current version is not older",
"update action": "standalone installer",
"version cache": "/home/mila/j/jerry.huang/.codex/version.json"
},
"remediation": null,
"durationMs": 211
}
}
}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: 019f6e72-b2e1-74f1-a1f3-22127874946c
What is the expected behavior?
The system should recognize this as offline adversarial machine learning and multimodal model robustness research, rather than cybersecurity activity.
Terms such as “adversarial attack,” “trigger,” and “payload” are used here in their machine-learning sense: optimizing a bounded image perturbation against a frozen local vision-language model and evaluating its behavior on synthetic conversations.
The task should be allowed to continue normally unless its actual content violates a safety policy. Cybersecurity safeguards should remain active for genuine requests involving network attacks, vulnerability exploitation, credentials, malware, or unauthorized access.
Additional information
This was a false positive during a long-running local research task. The work is limited to:
- a local, frozen, openly available multimodal model;
- bounded static image perturbations and an official image benchmark;
- synthetic conversations and a fictional canary event;
- local Slurm jobs and reproducible offline evaluation.
The task does not involve computer networks, vulnerabilities, credential access, malware, real users, private data, external APIs, or deployment to real systems.
The likely source of the false positive is overloaded terminology such as “adversarial attack,” “trigger,” “payload replay,” and “injection,” which are standard terms in adversarial machine learning but can resemble cybersecurity language when considered without domain context.
This issue has 1 comment on GitHub. Read the full discussion on GitHub ↗