commit-work
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local git commands (git status, git diff, git add, git commit) and repository-specific verification scripts (tests, linting) to manage code changes. These operations are performed in the local environment and are essential to the skill's purpose.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its handling of untrusted codebase data through git diff. * Ingestion points: Codebase changes are ingested via git status and git diff as defined in the SKILL.md workflow. * Boundary markers: No specific delimiters are used to isolate the ingested diff content from the agent's instructions. * Capability inventory: The agent can perform git commit and execute local verification scripts (Step 7 in SKILL.md). * Sanitization: No validation or filtering is applied to the codebase changes before they are processed for commit message generation.
Audit Metadata