glean-search
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
gleanCLI tool to perform searches and thejqutility to process JSON output. - [PROMPT_INJECTION]: Indirect prompt injection surface identified.
- Ingestion points: The skill retrieves search results from external enterprise data sources (e.g., Confluence, policies, engineering docs) using the
glean searchcommand. - Boundary markers: There are no explicit instructions or delimiters provided to help the agent distinguish between search result data and instructions.
- Capability inventory: The skill uses the
gleanCLI for data retrieval andjqfor manipulation. - Sanitization: No sanitization or filtering of the retrieved content is described in the skill definition.
Audit Metadata