The Agent Skills Directory

[SAFE]: The skill's primary function is to perform code reviews on local repository changes using standard git commands. It does not exhibit any malicious patterns.
[COMMAND_EXECUTION]: The skill uses "git diff" to retrieve code changes. This is a standard and expected operation for a code review tool.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data in the form of code diffs. This constitutes an ingestion point for untrusted data. However, the skill instructions are focused on passive analysis (reviewing) rather than active execution, which minimizes the risk of indirect prompt injection. While explicit boundary markers are not defined in the prompt, the skill's capabilities are limited to generating review text.

code-review