commit-message-crafter
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze staged changes using git diff. This introduces a potential surface where malicious content within the files being committed could attempt to influence the agent's summary or behavior.
- Ingestion points: Output of
git diff --stagedandgit diff --staged --name-onlyreferenced in SKILL.md. - Boundary markers: None present in the instructions to delimit the diff output.
- Capability inventory: Execution of shell commands including git, npm, and npx as described in SKILL.md.
- Sanitization: No specific sanitization or filtering of the diff output is mentioned before processing.
- [EXTERNAL_DOWNLOADS]: The skill references standard development tools available via the npm registry, such as commitlint and commitizen, which are well-known services in the developer ecosystem.
- [COMMAND_EXECUTION]: The skill uses shell commands to inspect the git state and configure git templates. These are standard operations for managing version control in a development environment.
Audit Metadata