context7-mcp

Warn

Audited by Snyk on Feb 21, 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.md workflow explicitly directs the agent to call Context7 MCP tools (e.g., mcp__context7__query-docs) to retrieve library/framework documentation and even falls back to tavily-mcp or WebFetch for official docs sites, meaning the agent will ingest and act on open/public third‑party documentation as part of its normal decision-making.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 21, 2026, 02:23 AM