library-docs

Warn

Audited by Snyk on Mar 1, 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.md explicitly describes connecting to the context7 MCP server and calling mcp__context7__get-library-docs to fetch public library documentation (e.g., React, Next.js, Supabase) which the agent loads and uses to guide implementations, so external third‑party docs can materially influence agent actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.80). The skill invokes the external context7 MCP server (configured as "npx -y @context7/mcp-server") at runtime to fetch documentation that is loaded into the agent's conversation context, so remote content from that server can directly control prompts.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 01:36 AM