The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes external system commands and local Python scripts to perform its analysis. Findings: subprocess.run calls in scripts/pr_analyzer.py to execute git and in scripts/review_report_generator.py to launch child analysis scripts. The execution environment depends on the repository path and git references provided during tool invocation.
[PROMPT_INJECTION]: The skill has an indirect prompt injection attack surface because it reads and analyzes content from untrusted source repositories. Ingestion points: File reading in scripts/code_quality_checker.py and git metadata retrieval in scripts/pr_analyzer.py. Boundary markers: The skill does not use specific delimiters or instructions to prevent the agent from potentially obeying instructions embedded within the code being reviewed. Capability inventory: Subprocess execution of git commands and local scripts. Sanitization: No sanitization or escaping of the ingested code content is performed before processing.

code-reviewer