list-feeds-skill
Warn
Audited by Snyk on Mar 8, 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). This skill's scripts/list-feeds.mjs calls an external MCP HTTP endpoint (MCP_SERVER_URL) to fetch and JSON-parse Xiaohongshu homepage feeds—public, user-generated social-media content the agent reads and returns as part of its workflow—so that untrusted content could influence subsequent agent behavior.
Audit Metadata