glean-insights
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
gleanCLI, a vendor-provided tool from gleanwork, to fetch search analytics and platform usage metrics. - [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection as it retrieves and processes data originating from end-user search patterns.
- Ingestion points: Analytics data containing user-generated search queries retrieved from the
glean insights getcommand. - Boundary markers: None identified; the skill does not instruct the agent to use delimiters or ignore embedded instructions within the returned data.
- Capability inventory: The skill provides the capability to execute shell commands (the
gleantool) and process output withjq. - Sanitization: There is no evidence of sanitization, filtering, or validation of the retrieved analytics data before it is ingested into the agent context.
Audit Metadata