context7

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill executes a local TypeScript script via the Bun runtime. This is standard operational behavior for its described functionality.
  • [EXTERNAL_DOWNLOADS] (LOW): The skill relies on an external third-party 'Context7 MCP service' to retrieve documentation and code examples, creating a dependency on an external provider.
  • [PROMPT_INJECTION] (LOW): The skill exhibits an Indirect Prompt Injection surface (Category 8c) because it fetches content from external, potentially untrusted sources (documentation for thousands of libraries). 1. Ingestion points: Data retrieved from the Context7 MCP service API. 2. Boundary markers: None provided in the instructions to delimit fetched content. 3. Capability inventory: The agent consumes retrieved documentation to provide technical guidance and generate code. 4. Sanitization: No sanitization of the external documentation content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:12 PM