thermos
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown instructions and YAML configuration. It does not include scripts, binaries, or external package dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of code diffs and file excerpts from Pull Requests or branches. This serves as a surface for indirect instructions, although the skill itself does not provide high-privilege execution capabilities.
- Ingestion points: Code diffs and file context excerpts (SKILL.md, Workflow step 2).
- Boundary markers: No specific delimiters or safety warnings for embedded instructions are defined in these instructions.
- Capability inventory: Launching specialized subagents for code analysis (SKILL.md, Workflow step 3).
- Sanitization: No explicit sanitization or filtering of the input diffs is mentioned.
Audit Metadata