code-reviewer
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to automatically ingest and analyze potentially untrusted source code and git diffs as part of its core functionality. It lacks specific instructions to the agent to establish boundary markers or to ignore instructions that might be embedded within the files being analyzed, which constitutes a minor surface for indirect prompt injection.
- Ingestion points: Source code files, git diff output, and code snippets mentioned in conversation (SKILL.md).
- Boundary markers: The skill instructions do not define delimiters or specific warnings to the agent to separate analysis logic from data.
- Capability inventory: Read, Grep, and Glob tools used for file system inspection (SKILL.md).
- Sanitization: No sanitization, escaping, or validation of the processed code content is specified.
Audit Metadata