ClawAudit verdict
mythosforge
The skill accesses credentials and API keys for a legitimate purpose of commissioning AI agents, but requires careful handling of sensitive information.
⚠ 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.
Findings (3)
Data encoding/decoding
SKILL.md · code
Base64 encoding/decoding
SKILL.md · prose · downgraded · base64-encode
Popular HTTP library — network access
SKILL.md · prose · downgraded · axios
Permissions & capabilities
No declared permissions — minimal attack surface.
credential_accessdata_encodingnetwork_in Is this flag fair?
Thanks — recorded.