community-mod-pack
Warn
Audited by Snyk on Feb 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests and analyzes user-generated channel logs and message exports from third-party platforms (see SKILL.md "Required inputs" and references/endpoints.md mentioning Discord/Telegram read APIs), so untrusted messages are read and can materially influence classification and drafted moderator actions, enabling indirect prompt injection.
Audit Metadata