The Agent Skills Directory

[SAFE]: The scripts provided in the scripts/ directory (pr_analyzer.py, code_quality_checker.py, and review_report_generator.py) are placeholder implementations that perform local path validation only. They do not execute remote code, perform network operations, or access sensitive system files.
[SAFE]: No obfuscation techniques, such as Base64 encoding of commands, zero-width characters, or homoglyph substitutions, were detected in the source code or documentation.
[INDIRECT_PROMPT_INJECTION]: The skill is intended to analyze external source code provided via the <project-path> or <target-path> arguments. This ingestion of untrusted data is a known attack surface for indirect prompt injection, though the provided implementation does not currently contain logic that would be vulnerable to execution.
[SAFE]: The SKILL.md and reference files contain standard technical documentation and do not include instructions designed to bypass agent safety filters or override system prompts.

code-reviewer