unblocked-context-search-documentation
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute the 'unblocked' CLI tool with the 'context-search-documentation' subcommand. This tool is a vendor-provided resource used for semantic search across integrated documentation platforms.
- [PROMPT_INJECTION]: The skill processes content from untrusted external documentation sources, establishing a surface for indirect prompt injection. This is an inherent risk for information retrieval skills. * Ingestion points: The agent ingests data returned by the 'unblocked context-search-documentation' tool into its context. * Boundary markers: There are no explicit delimiters or safety instructions provided to prevent the agent from following commands that might be embedded in the retrieved documentation. * Capability inventory: The skill notes the presence of other tools like Grep, Glob, and Read for interacting with the codebase. * Sanitization: The skill does not specify any sanitization, validation, or filtering processes for the content retrieved from external platforms.
Audit Metadata