glare-review-surface
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No security issues were detected. The skill provides coaching instructions and frameworks for design reviews without any dangerous capabilities.
- [NO_CODE]: The skill consists entirely of markdown instructions and references. It does not contain any executable scripts, shell commands, or external dependencies.
- [DATA_EXFILTRATION]: No network operations or sensitive file access patterns were found. The skill is purely conversational.
- [PROMPT_INJECTION]: The skill processes user-provided transcripts or snippets from design reviews. While this represents a potential surface for indirect prompt injection, the agent has no tools or capabilities (such as file system access or network requests) to exploit, rendering the risk negligible.
Audit Metadata