context7
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill makes HTTP GET requests to
https://context7.com/api/v2to retrieve documentation search results and content. This is the intended behavior for a documentation lookup service. - [COMMAND_EXECUTION]: The skill provides several TypeScript CLI tools (
c7-lookup,c7-resolve,c7-query) intended to be executed within the environment using thebunruntime. - [INDIRECT_PROMPT_INJECTION]: The skill ingests documentation content from an external source, creating a surface for potential indirect prompt injection attacks.
- Ingestion points: Documentation and search results are fetched via the API in
Tools/src/lib/context7.ts. - Boundary markers: None identified in the source code; external content is returned as raw markdown strings.
- Capability inventory: The skill has network access (GET requests to context7.com) and file system access (read/write access to a dedicated cache file at
~/.cache/context7/resolved.json). - Sanitization: None; content from the external API is processed directly by the agent.
Audit Metadata