writing-commit-messages
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses local shell commands including
git diff,jj diff,git commit, andjj committo analyze changes and apply the generated messages to the repository. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from git diffs which could contain malicious instructions designed to influence the generated commit message or the agent's behavior.
- Ingestion points: Output of
git difforjj diff(workflow section in SKILL.md). - Boundary markers: No delimiters or explicit instructions to ignore embedded content are used.
- Capability inventory: The skill has the ability to write to the repository via commit commands.
- Sanitization: No sanitization or validation of the diff content is performed before generating the commit message.
Audit Metadata