The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local commands to perform its analysis tasks.
scripts/pr_analyzer.py uses the subprocess module to run git diff and git log commands against the target repository.
scripts/review_report_generator.py executes internal scripts (pr_analyzer.py and code_quality_checker.py) to generate reports.
All commands are called with list arguments, which prevents shell command injection.
[PROMPT_INJECTION]: The skill processes external code files, which introduces a surface for indirect prompt injection.
Ingestion points: File contents and git diffs are read from the repository being analyzed in scripts/code_quality_checker.py and scripts/pr_analyzer.py.
Boundary markers: The skill does not currently implement specific delimiters or 'ignore' instructions for the content it extracts from files.
Capability inventory: The skill has read access to the local filesystem for the target directory and can execute git commands.
Sanitization: Analyzed code snippets are processed using regular expressions but are not explicitly sanitized before being included in the analysis reports.

code-reviewer