ClawAudit verdict

arena-council

45
🟠 Risky
Significant concerns — only install if you understand the risks

The skill explicitly imports and applies 'god_mode techniques' when all council models refuse due to censorship, which is a documented censorship-bypass mechanism; this is a concrete instruction to circumvent model safety guardrails, warranting RISKY.

⚠ 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.

68
security
60
transparency
70
maintenance

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (2)

Pattern match medium

HTTP request to bare IP address — common in malicious payloads

SKILL.md · prose · downgraded · http://127.0.0.1

Pattern match low

Python aiohttp session — async network access

scripts/council.py · prose · downgraded · aiohttp.ClientSession

Permissions & capabilities

No declared permissions — minimal attack surface.

network_outpackage_install

Is this flag fair?

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