ClawAudit verdict
publish-skill
clawhub-publish-helper
The skill helps prepare and publish OpenClaw skills to ClawHub, handling PII/secret auditing and env var extraction. The use of credential_access capability is concerning, although it seems intended for legitimate publishing purposes.
โ Flagged for review โ coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis โ not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (2)
Attempts to modify skills or system prompts
SKILL.md ยท prose ยท downgraded ยท edit instructions
Python os.environ.get โ reads environment variable
SKILL.md ยท code ยท os.environ.get(
Permissions & capabilities
No declared permissions โ minimal attack surface.
credential_access Is this flag fair?
Thanks โ recorded.