code-reviewer
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of local Python scripts, including pr_analyzer.py, code_quality_checker.py, and review_report_generator.py, to perform analysis on user-specified code repositories. These executions are consistent with the skill's stated purpose of automated code review.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and process untrusted external data in the form of pull request diffs and source code files. Ingestion points: Repository paths and file contents provided during tool execution (SKILL.md). Boundary markers: No explicit delimiters or instructions are used to separate untrusted code content from the agent's internal reasoning. Capability inventory: The skill utilizes local command execution to run analysis scripts. Sanitization: There is no evidence of sanitization for textual content or comments within the processed code files.
Audit Metadata