smithery-homepage
Warn
Audited by Snyk on May 2, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the app to call external MCP tools via the Smithery Connect API (see the callMcpTool implementation and the requirement to run
smithery mcp call <connection> <tool>to generate/copy schemas), which fetches and parses arbitrary third-party/tool outputs (e.g., Linear, Gmail, Notion) that the skill then reads and uses at runtime—exposing the agent to untrusted, user-generated remote content that can influence behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata