One CLI for all your AI coding agents - versions, config, cloud dispatch, sessions, and teams (now with first-class Grok Build CLI support)
D high
- capability exposure inferred + 35
- recent drift inferred + 20
- tool safety inferred + 12
- supply-chain attested + 6
- trust mitigators mixed − 3
attested inferred mixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
grade last moved 3d ago · see ecosystem CVEs →
- D · 62 → D · 70
- C · 50 → D · 62
- C · 44 → C · 50
- C · 47 → C · 44
- B · 34 → C · 47
- C · 47 → B · 34
- A · 0 → C · 47
Inferred surface — each links to servers holding it:
No known CVEs for this server.
- high dangerous code
committed secret: Anthropic key, Google OAuth client secret, OpenAI key · dynamic exec: new Function() · credential logged in 1 file(s) · obfuscated payload: dynamic require()/imp…
prompt-surface
shipped agent-instruction files + hidden-content / dangerous-code findings —
quoted from the analyzed source
analyzed v1.22.50 · analyzer v33 · 2w ago
skills & prompt files 17
- agent-rules phnx-labs-agi-cli-9006de7/AGENTS.md
- agent-rules phnx-labs-agi-cli-9006de7/cli/AGENTS.md
- agent-rules phnx-labs-agi-cli-9006de7/cli/src/lib/daemon/AGENTS.md
- skill phnx-labs-agi-cli-9006de7/cli/tests/fixtures/project-resources/repo/.agents/skills/myskill/SKILL.md
- agent-rules phnx-labs-agi-cli-9006de7/native/computer-mac/AGENTS.md
- agent-rules phnx-labs-agi-cli-9006de7/native/computer-win/AGENTS.md
- agent-rules phnx-labs-agi-cli-9006de7/packages/agi-cli/AGENTS.md
- agent-rules phnx-labs-agi-cli-9006de7/packages/session-tracker/AGENTS.md
- agent-rules phnx-labs-agi-cli-9006de7/packages/swarmify-mirror/AGENTS.md
- skill phnx-labs-agi-cli-9006de7/skills/browser/SKILL.md
- skill phnx-labs-agi-cli-9006de7/skills/devices/SKILL.md
- skill phnx-labs-agi-cli-9006de7/skills/routines/SKILL.md
- skill phnx-labs-agi-cli-9006de7/skills/run/SKILL.md
- skill phnx-labs-agi-cli-9006de7/skills/secrets/SKILL.md
- skill phnx-labs-agi-cli-9006de7/skills/sessions/SKILL.md
- skill phnx-labs-agi-cli-9006de7/skills/teams/SKILL.md
- skill phnx-labs-agi-cli-9006de7/skills/workflows/SKILL.md
danger signals17
- dynamic code execution new Function() phnx-labs-agi-cli-9006de7/cli/src/lib/traces/worker-template.test.ts :56
const fn = new Function( - suspicious endpoint mcp.posthog.com (telemetry) phnx-labs-agi-cli-9006de7/cli/src/commands/inspect.test.ts :474
expect(summarizeMcp({ name: 'posthog', transport: 'http', url: 'https://mcp.posthog.com' })) - over-broad OAuth scope https://mail.google.com/ phnx-labs-agi-cli-9006de7/cli/src/lib/browser/domain-skills.test.ts :77
const r = resolveDomainSkill('https://mail.google.com/mail/u/0/'); - committed secret Anthropic key phnx-labs-agi-cli-9006de7/cli/src/commands/accounts.test.ts :247
sk-ant…(35 chars, redacted) - committed secret Anthropic key phnx-labs-agi-cli-9006de7/cli/src/lib/__tests__/runner.test.ts :463
sk-ant…(34 chars, redacted) - committed secret Google OAuth client secret phnx-labs-agi-cli-9006de7/cli/src/lib/accounting/usage.ts :3347
GOCSPX…(35 chars, redacted) - committed secret Anthropic key phnx-labs-agi-cli-9006de7/cli/src/lib/claude-account-token.test.ts :78
sk-ant…(36 chars, redacted) - committed secret Anthropic key phnx-labs-agi-cli-9006de7/cli/src/lib/crabbox/runtimes.test.ts :269
sk-ant…(31 chars, redacted) - committed secret Anthropic key phnx-labs-agi-cli-9006de7/cli/src/lib/exec.test.ts :1174
sk-ant…(45 chars, redacted) - committed secret Anthropic key phnx-labs-agi-cli-9006de7/cli/src/lib/harness/adapters/claude.test.ts :56
sk-ant…(32 chars, redacted) - committed secret OpenAI key phnx-labs-agi-cli-9006de7/cli/src/lib/session/trajectory-html.compare.test.ts :45
sk-sup…(29 chars, redacted) - committed secret OpenAI key phnx-labs-agi-cli-9006de7/cli/src/lib/session/trajectory-html.test.ts :43
sk-sup…(29 chars, redacted) - committed secret OpenAI key phnx-labs-agi-cli-9006de7/cli/src/lib/session/trajectory-text.compare.test.ts :56
sk-sup…(29 chars, redacted) - committed secret OpenAI key phnx-labs-agi-cli-9006de7/cli/src/lib/session/trajectory-text.test.ts :110
sk-sup…(29 chars, redacted) - committed secret OpenAI key phnx-labs-agi-cli-9006de7/cli/src/lib/session/trajectory.test.ts :207
sk-sup…(29 chars, redacted) - committed secret Anthropic key phnx-labs-agi-cli-9006de7/cli/src/lib/share/publish.test.ts :978
sk-ant…(33 chars, redacted) - credential in logs credential in log phnx-labs-agi-cli-9006de7/cli/src/commands/secrets.ts :2664
console.log(password);
- recent drift +20 capability drift →
- supply-chain +6 supply-chain hub →
[](https://mcpobservatory.com/servers/github:phnx-labs/agents-cli/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of phnx-labs.