The Agent Skills Directory

[SAFE] (SAFE): No malicious patterns, hardcoded credentials, or unauthorized network operations were detected in the scripts or documentation.
[INDIRECT_PROMPT_INJECTION] (LOW): As a code review tool, the skill is designed to process external, potentially untrusted code. This creates a surface for indirect prompt injection where malicious instructions embedded in reviewed files could attempt to influence agent behavior. The current boilerplate scripts do not implement sensitive capabilities that could be exploited via this vector.
Ingestion points: scripts/pr_analyzer.py, scripts/code_quality_checker.py, and scripts/review_report_generator.py take a target path for processing.
Boundary markers: Not implemented in current boilerplate.
Capability inventory: Scripts currently only perform local path validation and print placeholder results to stdout.
Sanitization: Not implemented in current boilerplate.

code-reviewer