Context7 MCP Documentation Server for LLM Code Editors

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill guides the user to install the ctx7 package globally and execute it using npx ctx7 setup. This process downloads and runs code from the NPM registry to configure the local environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to fetch version-specific documentation and code examples from external sources at query time and inject them into the AI's prompt. This creates a surface for indirect prompt injection if the source documentation contains malicious instructions designed to influence the LLM.
  • Ingestion points: Documentation and code examples are pulled from external sources (web/GitHub) at query time (described in SKILL.md).
  • Boundary markers: The skill does not define specific delimiters or "ignore instructions" markers to isolate the fetched documentation from the agent's core instructions.
  • Capability inventory: The tool is designed for LLM Code Editors, which typically have capabilities for file modification and command execution.
  • Sanitization: There is no mention of sanitization or validation of the remote content before it is interpolated into the prompt context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 02:22 AM
Security Audit — agent-trust-hub — Context7 MCP Documentation Server for LLM Code Editors