pre-push-review

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local git commands including status, diff, and ls-files to inspect the working tree and pending changes.
  • [COMMAND_EXECUTION]: It identifies and runs verification scripts (test, lint, typecheck) found within the project's source code and configuration files.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because its execution workflow is dependent on instructions extracted from external project files.
  • Ingestion points: Extracts verification commands from 'pyproject.toml', 'package.json', 'README.md', and CI configuration files.
  • Boundary markers: No protective delimiters or explicit instructions to ignore embedded malicious content are present.
  • Capability inventory: Subprocess execution of arbitrary project-defined scripts.
  • Sanitization: No validation or escaping is applied to the command strings derived from project metadata and documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 05:58 AM