The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were detected. The skill performs legitimate code review automation tasks.
[COMMAND_EXECUTION]: The scripts pr_analyzer.py and review_report_generator.py use subprocess.run to execute git commands and internal sub-scripts. These calls are implemented safely using argument lists and do not invoke a shell, mitigating command injection risks.
[DATA_EXFILTRATION]: No network activity or external data transmission was found. The scripts process local files and repository metadata to generate reports.
[PROMPT_INJECTION]: The skill processes untrusted input from reviewed code, creating a surface for indirect prompt injection. 1. Ingestion points: pr_analyzer.py and code_quality_checker.py read file content and diffs. 2. Boundary markers: Absent; reports include code snippets without explicit instructions to the AI agent. 3. Capability inventory: The skill uses subprocess.run for local tools. 4. Sanitization: Absent for content processing, but deterministic pattern matching is used instead of execution. The risk is minimal.

code-reviewer