The Agent Skills Directory

[SAFE]: The skill follows standard practices for code review automation using local git diff and git log commands to analyze code changes. No malicious code or exfiltration patterns were identified.
[DATA_EXPOSURE]: The skill reads repository content, commit messages, and documentation files to perform its review. This is the intended primary purpose of the skill and does not involve sending data to unauthorized external endpoints.
[PROMPT_INJECTION]: As a code review tool, the skill processes untrusted input from diffs and project documentation, which presents a surface for indirect prompt injection (Category 8). This is a known risk for agents performing content analysis, and the skill's instructions do not include specific boundary markers to mitigate this, though the overall risk remains low within the intended execution context.

review