The Agent Skills Directory

[SAFE]: The skill uses dynamic context injection via !git commands to populate repository status into the prompt. This is a legitimate use of the feature for local context gathering.- [SAFE]: Section 3 provides explicit security guidance for the agent to identify and exclude credentials, secrets, and private keys from commits, mitigating data exposure risks.- [SAFE]: The skill processes local file changes, which constitutes an indirect prompt injection surface. Evidence chain: 1. Ingestion points: File contents read via git diff and git status. 2. Boundary markers: Not explicitly used. 3. Capability inventory: git add and git commit tools. 4. Sanitization: Detailed instructions for the agent to review content for accidental debug statements, logs, and secrets before committing.

commit