The Agent Skills Directory

[SAFE]: The skill is designed to improve code quality by analyzing repository changes. It identifies changes using git diff and performs analysis through specialized sub-agents. All operations are local and consistent with the skill's stated purpose.
[PROMPT_INJECTION]: The skill features a surface for indirect prompt injection because it ingests untrusted content (the codebase and diffs) and has the ability to modify files via the Edit tool.
Ingestion points: Code changes and file contents are read using git diff, Read, Grep, and Glob tools.
Boundary markers: There are no explicit delimiters or instructions to the agent to ignore embedded commands within the code being reviewed.
Capability inventory: The skill utilizes Bash (for git operations), Edit (for fixing issues), and the Agent tool for task delegation.
Sanitization: No sanitization or validation of the processed code content is performed, meaning instructions hidden in comments could potentially be interpreted by the review agents.

claude-simplify