find-docs
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill triggers the download of the 'ctx7' package from the public npm registry using commands like
npm install -g ctx7@latestandnpx ctx7@latestas a fallback mechanism when MCP tools are unavailable.\n- [COMMAND_EXECUTION]: The skill utilizes shell commands to interact with the system, specifically invokingnpm,npx, and thectx7CLI for its core functionality of resolving library identifiers and fetching documentation.\n- [INDIRECT_PROMPT_INJECTION]: \n - Ingestion points: External documentation and code examples ingested through
mcp__plugin_context7_context7__query-docsorctx7 docsas described inSKILL.md.\n - Boundary markers: Absent. The skill provides no instructions to wrap or delimit external content to prevent the agent from executing instructions found within the documentation.\n
- Capability inventory: The skill allows shell command execution (
npm,npx,ctx7) across its workflow as described inSKILL.md.\n - Sanitization: Absent. The skill does not implement any escaping or validation logic for the external content retrieved from the Context7 service.
Audit Metadata