agency-client
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to use file search utilities (Glob and Grep) to identify relevant client records in the workspace. These operations are limited to data retrieval within the local environment.
- [PROMPT_INJECTION]: The skill processes content from local files (markdown, JSON, PDF), which introduces a surface for indirect prompt injection. However, because the skill's functionality is limited to formatting a terminal summary and lacks network access or executable sinks, the risk of exploitation is negligible.
Audit Metadata