human-loop-audit
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to launch external applications using commands like 'Start-Process' to allow the user to perform live testing. This is the primary functional behavior of the audit workflow.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user feedback from the chat (Ingestion Point) to generate structured findings and delegate repairs using shell commands (Capability Inventory). While there are no specific boundary markers or sanitization steps mentioned for the feedback, this is a standard design for a human-in-the-loop process.
Audit Metadata