glean-messages
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes the
gleanCLI tool, a resource associated with the vendor 'gleanwork', to interact with the Glean service and retrieve message data. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface due to its handling of external message data.
- Ingestion points: Untrusted message content from external platforms (e.g., Slack, Teams) is ingested via the
glean messages getcommand in SKILL.md. - Boundary markers: No explicit markers or 'ignore' instructions are used to distinguish ingested message data from agent instructions.
- Capability inventory: The skill has the capability to execute shell commands via the
gleanCLI tool to fetch data. - Sanitization: No sanitization or validation of the retrieved message content is performed before it is processed by the agent.
Audit Metadata