thermo-run
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it processes untrusted external data.
- Ingestion points: Processes user requests, PR metadata, and branch diffs to determine review scope (SKILL.md).
- Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore embedded commands within the processed files.
- Capability inventory: Orchestrates two sub-skills (/skill:thermo-nuclear-review and /skill:thermo-nuclear-code-quality-review) and synthesizes their output into a final verdict.
- Sanitization: No sanitization or filtering of external content is performed before interpolation into the review context.
Audit Metadata