claude-code
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions specify external documentation sources from a non-trusted domain (context7.com). This constitutes an indirect prompt injection surface as the agent is told to load content from an unverified third-party service into its context.
- Ingestion points: The 'Documentation sources' section in
skill.mdprovides URLs for fetching site content for the agent to read. - Boundary markers: There are no explicit boundary markers or instructions to disregard potential commands embedded in the external data.
- Capability inventory: As documented in the skill, the environment supports powerful capabilities including bash shell execution, file read/write, and broad network access through MCP servers.
- Sanitization: No sanitization or validation of the fetched content is required or specified before it is processed by the agent.
Audit Metadata