clawhub-moderation
Warn
Audited by Socket on Jul 31, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
The skill is internally consistent with a ClawHub staff moderation purpose and uses a repo-local admin workflow rather than an obviously unrelated tool. Risk is still high because it grants an AI agent the ability to take consequential moderation and email actions with privileged credentials, even though the documented confirmations and dry-run steps reduce signs of malicious intent.
Confidence: 84%Severity: 72%
Audit Metadata