AGENT LAB: SKILLS

smithery

Warn

Audited by Snyk on Feb 15, 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 explicitly instructs the agent to discover and connect to arbitrary public MCP servers and the Smithery registry (e.g., smithery mcp search / smithery mcp add "https://..."), to call tools (smithery tool call) and to read skill reviews and search results (smithery skill search / skill review list), which are untrusted, user-provided third‑party content the agent will fetch and interpret.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:13 PM