commit
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
git,gh(GitHub CLI), andglab(GitLab CLI) commands to manage branches, stage changes, and create commits. These actions are within the expected scope for version control management. - [PROMPT_INJECTION]: The skill reads external data such as worktree diffs and project documentation (
CLAUDE.md,AGENTS.md) which could contain malicious instructions (Indirect Prompt Injection). Ingestion points: Git diffs, status outputs, and project-specific instruction files. Boundary markers: Absent; there are no specific delimiters or instructions to ignore potential commands within the files being read. Capability inventory: Includes file staging (git add), committing (git commit), and branch management (git switch,git rebase). Sanitization: Absent; the skill does not explicitly sanitize or validate the content of the diffs or files before processing them.
Audit Metadata