setup-mcp
Warn
Audited by Snyk on Apr 28, 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). The skill's SKILL.md instructs adding a .mcp.json with an external "url" (e.g., "https:///mcp/" and the example github endpoint) so the agent will call and ingest content from arbitrary third‑party MCP servers, which could supply untrusted instructions that affect tool behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata