The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes standard git commands including git diff, git status, git log, git commit, and git push to perform its core functions of reviewing code changes and managing repositories.
[COMMAND_EXECUTION]: The instructions recommend running external security scanning tools such as gitleaks, trufflehog, git secrets, and detect-secrets if they are present on the host system to identify leaked credentials.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input in the form of code diffs, which could theoretically contain malicious content designed to influence the agent's behavior during the review process.
Ingestion points: The output of git diff and git status commands executed in SKILL.md.
Boundary markers: None explicitly defined for separating the diff content from instructions.
Capability inventory: The skill has the capability to execute git commit and git push commands based on its analysis.
Sanitization: No specific sanitization logic is described for the diff content before it is processed by the AI.

ship-this