thermo-nuclear-code-quality-review
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze external, untrusted data (the "current branch's changes"). This creates a surface for indirect prompt injection attacks.
- Ingestion points: The agent processes the current branch's codebase and pull request changes as specified in the "Core Prompt".
- Boundary markers: The instructions do not define clear delimiters or provide the agent with a "system vs. data" context to help it ignore instructions embedded in code comments or strings.
- Capability inventory: The skill is designed to work within an agent environment that typically has file system access (read/write) and shell execution capabilities.
- Sanitization: There is no requirement or mechanism mentioned to sanitize, filter, or escape the content of the files being reviewed before the agent processes them.
- [NO_CODE]: The skill consists entirely of Markdown instructions and platform configuration metadata. It does not include executable scripts, binaries, or third-party dependencies.
Audit Metadata