Caveat verdict

agentic-engineering

agentic-beehive

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Architecture/framework documentation for a multi-agent orchestration pattern (agentic-engineering); contains no executable code, no credential handling, and no network calls — the executionSinkDetected flag is a false positive from illustrative pseudocode examples showing agent coordination philosophy.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

23
security
90
transparency
70
maintenance

Findings (8)

Pattern match critical

Possible hardcoded credential

composing/SKILL.md · code · TOKEN = "eyJhbG…tpzo

Pattern match medium

subprocess execution — runs system commands from Python

ai-daily-report/brewer/feishu_push.py · prose · downgraded · subprocess.run(

Pattern match medium

References agent memory files

coding/SKILL.md · code · memory.md

Pattern match medium

Opens WebSocket connection

composing/SKILL.md · code · WebSocket

Pattern match medium

POSTs data to external URL

composing/SKILL.md · code · .post("http://

Pattern match low

Python urllib.request — network access

ai-daily-report/forager/forager.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

mcp-server/server.py · prose · downgraded · os.environ.get(

Pattern match low

Python httpx request — network access

mcp-server/server.py · prose · downgraded · httpx.get(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API