ClawAudit verdict
alvis-advanced-skill-creator
A meta-skill that guides the agent through a documented 5-step research workflow for creating OpenClaw skills, using SKILLBOSS_API_KEY for AI-assisted generation; all described actions are transparent and purposeful.
⚠ 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
UPLOAD_INSTRUCTIONS.md · code · API_KEY="your_skillboss_api_key
Possible prompt injection — attempts to redefine agent identity
SKILL.md · prose · downgraded · You are now
Python os.environ.get — reads environment variable
scripts/advanced_skill_processor.py · prose · downgraded · os.environ.get(
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.