grill-me
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructional text for a requirements-gathering interview process. No executable code or scripts are included.
- [SAFE]: No network requests, sensitive file access, or data exfiltration patterns were identified.
- [SAFE]: No prompt injection, obfuscation, or persistence techniques were detected in the instructions or metadata.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow to ingest and process user-provided product ideas during an interview. While this creates a data ingestion surface, the agent's capabilities are restricted to conversational interaction and generating markdown documentation (e.g., IDEA_SCOPE.md), with no access to sensitive system tools or network operations.
Audit Metadata