thermo-nuclear-review
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection by processing external, potentially untrusted data.
- Ingestion points: The agent is instructed to read code diffs from checked-out branches and fetch pull request discussions using the 'gh' or 'glab' CLI tools.
- Boundary markers: The instructions lack explicit delimiters or 'ignore embedded instructions' warnings to separate the system prompt from the data being analyzed.
- Capability inventory: The skill uses 'gh' and 'glab' CLI tools (found in SKILL.md) to interact with remote repositories.
- Sanitization: No sanitization, escaping, or validation of the ingested code or PR comments is performed before processing.
Audit Metadata