git-commit-message
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it analyzes untrusted data from git diff output.
- Ingestion points: The skill reads staged changes using git diff commands (Workflow Step 1).
- Boundary markers: No explicit delimiters are mentioned to separate the diff content from instructions.
- Capability inventory: The skill executes local git commands and generates text output.
- Sanitization: No sanitization of the diff content is described.
- [COMMAND_EXECUTION]: The skill executes local git commands such as 'git diff --staged' and 'git status' to inspect staged changes. These are standard operations for the skill's purpose.
Audit Metadata