The Agent Skills Directory

[SAFE]: No malicious patterns or behaviors were identified. The skill is designed for standard Git workflow automation.
[COMMAND_EXECUTION]: The skill uses local Git commands such as git diff, git status, git add, and git commit to manage changes. It includes a 'Git Safety Protocol' that explicitly restricts the use of destructive flags (e.g., --force, hard reset) and prevents modifications to the global git configuration.
[DATA_EXFILTRATION]: The skill includes proactive security instructions to prevent the exposure of sensitive data, specifically instructing the agent to never commit files like .env, credentials.json, or private keys.
[PROMPT_INJECTION]: The skill presents a low risk of indirect prompt injection. While it ingests untrusted data from the local filesystem (via git diff), its capabilities are scoped to Git operations, and it follows a strict protocol that limits the impact of potentially malicious content embedded in files being committed.
Ingestion points: File content analyzed via git diff and git diff --staged in SKILL.md.
Boundary markers: None explicitly used for diff isolation.
Capability inventory: git add and git commit operations via the Bash tool.
Sanitization: The skill enforces strict formatting (Conventional Commits) and length constraints on the generated output.

git-commit