documentation-lookup
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches and processes content from an external documentation service (Context7 MCP). This introduces an attack surface where instructions embedded in the retrieved documentation could attempt to hijack the agent's logic or influence its output.
- Ingestion points: The skill ingests data from external sources through the
query-docstool inSKILL.md. - Boundary markers: The skill does not define specific delimiters or instructions to the agent to ignore any embedded directives within the fetched documentation content.
- Capability inventory: While the skill itself does not invoke shell commands or file writes, it relies on the agent's ability to execute tools that perform network operations.
- Sanitization: The skill implements a best practice by instructing the agent to redact sensitive data from the user's query before transmission, but it lacks sanitization for the incoming documentation snippets.
Audit Metadata