code-reviewer
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill documentation includes examples for running a helper Python script (
review.py) located within the skill's own installation path (~/.claude/skills/code-reviewer/scripts/). This script serves as the primary engine for the code review logic and is a standard component of the skill's functionality. - [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection due to its core function of analyzing external source code.
- Ingestion points: Content from source files (
--file,--dir) and Git diffs (--git-diff). - Boundary markers: The documentation does not specify the use of delimiters or specific instructions to the model to ignore embedded commands within the code being analyzed.
- Capability inventory: The skill is restricted to generating review reports and does not exhibit capabilities for outbound network requests, sensitive file access (beyond the target code), or persistence.
- Sanitization: There is no evidence of filtering or escaping logic for instructions that might be hidden within code comments or string literals.
Audit Metadata