code-review
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents an attack surface for indirect prompt injection as it is designed to ingest and analyze untrusted external code and diffs.
- Ingestion points: The skill reads code files and git diffs from the local environment for analysis.
- Boundary markers: The workflow includes a mandatory 'AI Self-Check' which requires the agent to cite specific evidence and read the full context of code, providing a mitigation against accidental execution of embedded instructions.
- Capability inventory: The instructions call for the execution of various local linters and CLI tools (including tsc, eslint, ruff, mypy, shellcheck, terraform, and ansible-lint) and performs git operations to gather context.
- Sanitization: There is no explicit process defined in the instructions for sanitizing or escaping external code content before it is processed by the LLM.
Audit Metadata