The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the git CLI to identify modified files for review. This is a standard and expected operation for a code analysis tool.
[PROMPT_INJECTION]: The skill processes external code content, creating a surface for indirect prompt injection. This is inherent to its primary purpose as a code reviewer.
Ingestion points: Code content retrieved from the local repository via git commands in SKILL.md.
Boundary markers: Absent; the skill does not explicitly use delimiters or instructions to ignore embedded commands within the code being analyzed.
Capability inventory: File system read access via git and the ability to spawn subagents using the Agent tool.
Sanitization: None; the skill passes raw code data to the subagent for review.

code-reviewer