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 glean CLI tool to perform searches and the jq utility 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 search command.
  • 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 glean CLI for data retrieval and jq for manipulation.
  • Sanitization: No sanitization or filtering of the retrieved content is described in the skill definition.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 12:14 AM