announcekit

Warn

Audited by Snyk on Mar 4, 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). The SKILL.md explicitly instructs using the Membrane CLI to run actions like "list-posts", "get-post", "list-feedbacks" and to proxy requests to the AnnounceKit API (e.g., membrane action run and membrane request), which will fetch and surface user-generated/public AnnounceKit content that the agent is expected to read and could influence its subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 08:58 AM