roast
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions guiding the agent's reasoning process for critiquing artifacts (files, snippets, plans).
- [SAFE]: No network operations, external downloads, or remote code execution patterns were detected.
- [SAFE]: No sensitive file access or credential exposure risks are present.
- [SAFE]: The skill does not utilize any tools or execute shell commands, eliminating categories like privilege escalation or persistence.
- [SAFE]: While the skill is designed to process untrusted data (artifacts provided by the user), its only output is text critique, and it lacks the capabilities (like file writing or code execution) to make indirect prompt injection a significant risk.
Audit Metadata