ce-commit
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes several git commands (
git status,git log,git diff,git checkout,git add,git commit) and the GitHub CLI (gh repo view). The instructions specifically mandate individual shell tool calls without command chaining (pips, redirects, or logical operators) to maintain cross-platform stability and reduce injection risks. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and interpret untrusted data from the local environment to determine its workflow.
- Ingestion points: Output from
git log(commit history),git diff(uncommitted code changes), andgh repo view(repository metadata) is read into the agent's context (SKILL.md). - Boundary markers: Absent; the instructions do not require the use of delimiters or 'ignore' instructions when processing external data to generate commit messages or branch names.
- Capability inventory: The skill has the ability to execute shell commands and write files to the filesystem (SKILL.md).
- Sanitization: None; there are no instructions to sanitize, escape, or filter the content of commit logs or diffs before they are used to generate new commit messages.
Audit Metadata