git-cp
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a routine Git operation workflow. It delegates tasks to an internal subagent (
git-manager) and focuses on task planning and descriptive commit messaging. - [PROMPT_INJECTION]: The skill ingests untrusted data in the form of local file changes to generate commit messages and plan tasks. This represents an indirect prompt injection surface where malicious instructions embedded in file changes could potentially influence the agent's behavior during the task planning or commit phases. However, the scope is limited to Git operations.
- Ingestion points: Reads repository changes and file contents (referenced in SKILL.md task planning instructions).
- Boundary markers: No explicit delimiters or safety warnings for handling embedded instructions in the file content are defined.
- Capability inventory: Performs Git staging, committing, and pushing via the
git-managersubagent. - Sanitization: No validation or sanitization of the file content is performed before processing.
Audit Metadata