mcp-provider
Warn
Audited by Snyk on Apr 17, 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's discovery workflow (discover_mcp.py and SKILL.md) explicitly fetches and ingests MCP catalogs from approved_sources such as the public GitHub URL https://github.com/modelcontextprotocol/servers and also accepts arbitrary --source URLs, meaning it consumes public third‑party catalog content that can directly influence which tools and runtimes are attached and used.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata