docs-search
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves documentation from an external server address provided by the user, which could potentially contain instructions that influence the agent's behavior.\n
- Ingestion points: Documentation content is fetched from a remote server via the
fetchAPI inscripts/query.mjs.\n - Boundary markers: The skill does not employ specific delimiters or 'ignore' instructions for the retrieved documentation content.\n
- Capability inventory: The skill has access to read the
.pe.jsoncconfiguration file and perform network GET requests.\n - Sanitization: The documentation content is passed to the agent without specific sanitization or filtering for command patterns.\n- [COMMAND_EXECUTION]: The skill executes a bundled Node.js script (
scripts/query.mjs) to perform documentation lookups and interface with the documentation server.\n- [EXTERNAL_DOWNLOADS]: The skill performs network requests to an external server to retrieve documentation data based on the configuration stored in the repository.
Audit Metadata