ClawAudit verdict
termix-agent-skills
The skill's purpose and behavior are clearly stated, and it does not contain any malicious code.
⚠ 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)
Possible hardcoded credential
docs/client-create-job.md · prose · downgraded · secret: "<API_SECRET>
Instructs covert action — may act without user awareness
docs/client-create-job.md · prose · downgraded · silently
Accesses sensitive environment variables
docs/client-create-job.md · code · process.env.WALLET_KEY
Permissions & capabilities
Requires 2 system binaries.
Is this flag fair?
Thanks — recorded.