announcekit
Warn
Audited by Snyk on Apr 29, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). This skill uses Membrane to fetch user-generated AnnounceKit content (e.g., list-posts, get-post, list-feedbacks shown in SKILL.md), meaning the agent will ingest untrusted third-party posts/feedback that could contain instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata