recovery-community-moderator

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly processes user-generated forum posts and comments (see the "Moderating forum posts and comments" usage and scripts/moderate_content.py which sends arbitrary post content to the Claude model), so it ingests untrusted third‑party content that could carry indirect prompt injections.