ClawAudit verdict
office-link
mx-link
The skill is designed to manage third-party accounts and proxy API calls. It requires credentials but seems to handle them securely.
⚠ 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 (2)
Possible hardcoded credential
SKILL.md · prose · downgraded · API_KEY="mk_your_key_here
Accesses OpenClaw config/secrets directly
SKILL.md · code · ~/.openclaw/.env
Permissions & capabilities
Requires 1 environment variable. (1 sensitive: [MORPHIXAI_API_KEY]).
credential_access Is this flag fair?
Thanks — recorded.