ClawAudit verdict
ai-company
The skill accesses various capabilities including credential_access, which could potentially be used to exfiltrate 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.
Permission integrity
credential_access
package_install
agent_memory
Findings (2)
Possible hardcoded credential
SKILL.md · code · api_key: "${ANTHROPIC_API_KEY}
References webhook/callback URL
SKILL.md · code · webhook_url
Permissions & capabilities
No declared permissions — minimal attack surface.
package_installcredential_accessagent_memorynetwork_in Is this flag fair?
Thanks — recorded.