ClawAudit verdict

cnexus2-cognitive-os

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

The content describes a local cognitive architecture and does not contain concrete code that exfiltrates data or executes harmful commands.

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

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

55
security
70
transparency
70
maintenance

Findings (4)

Pattern match high

HTTP request to bare IP address — common in malicious payloads

README.md · code · http://127.0.0.1

Pattern match high

Possible hardcoded credential

ui/_next/static/chunks/878-06fdd47559cd8c8c.js · prose · downgraded · apiKey:"本地 Ollama 无需 Key

Pattern match low

Python urllib.request — network access

src/llm_adapter.py · prose · downgraded · urllib.request

Pattern match low

Opens WebSocket connection

ui/_next/static/chunks/878-06fdd47559cd8c8c.js · prose · downgraded · WebSocket

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/D/G). 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