thermos
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill functions solely as an orchestration layer for managing code review tasks across internal subagents. It does not perform any direct system operations or network requests.
- [NO_CODE]: There are no executable scripts, shell commands, or binary files associated with this skill. It relies entirely on natural language instructions to guide the agent's behavior.
- [INDIRECT_PROMPT_INJECTION]: While the skill is designed to ingest and process untrusted data (such as pull request diffs and changed files), it lacks the capabilities (e.g., shell execution, file writing, or network access) that would make such an injection exploitable.
- Ingestion points: Processes PR content, branch diffs, and file context (SKILL.md).
- Boundary markers: None explicitly defined in the instructions.
- Capability inventory: No subprocess calls, file-system writes, or network operations are present.
- Sanitization: No specific sanitization or escaping logic is implemented for the reviewed code context.
Audit Metadata