thermos
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill acts as a coordinator for specialized subagents and contains only natural language instructions. It does not contain scripts, shell commands, or direct network access.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from pull requests and diffs. Ingestion points: Git diffs and file context (SKILL.md). Boundary markers: None explicitly defined. Capability inventory: Launching subagents for code review. Sanitization: None explicitly mentioned. As this is a code review tool, this surface is expected.
Audit Metadata