git-commit
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes several Bash scripts (
repo-discover.sh,repo-status.sh,git-commit.sh,git-push.sh) to perform file system traversal and git operations. These actions are intended for repository management and are scoped to the local environment. - [PROMPT_INJECTION]: The skill is subject to indirect prompt injection as it processes untrusted data from repository diffs and status reports to generate commit messages.
- Ingestion points:
git statusandgit diffoutputs processed by the agent inSKILL.mdandSKILL.ko.md. - Boundary markers: None; the instructions do not define delimiters to isolate diff content from the agent's instructions.
- Capability inventory: Subprocess execution (Bash), file modifications (git commits), and network access (git push via
git-push.sh). - Sanitization: None; the skill relies on raw diff output for its logic.
Audit Metadata