clawhub-moderation

Warn

Audited by Socket on Jul 31, 2026

1 alert found:

Security
SecurityMEDIUM
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
Analyzed At
Jul 31, 2026, 08:24 PM
Package URL
pkg:socket/skills-sh/steipete%2Fclawdhub%2Fclawhub-moderation%2F@0bed9a8743c53af87d4f76d0c28e8451f87a08af0f77ab7f7b57b9d0b5223179
Security Audit — socket — clawhub-moderation