write-frontend-tests
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes standard git commands (
git diff) to identify changes between branches and usesgrepfor filtering. These are expected for a skill designed to assist with branch-specific testing. - [COMMAND_EXECUTION]: The skill uses
pnpmfor running tests, formatting, and linting (pnpm test:unit,pnpm format, etc.). This is the standard package manager behavior for the target project. - [METADATA_POISONING]: The metadata correctly identifies the author as 'autogpt-team' and the version as '1.0.0'. No deceptive instructions or injections were found in the description or arguments fields.
- [REMOTE_CODE_EXECUTION]: While the skill involves writing and executing code, it is limited to the local environment and the project's own test suite. There are no patterns involving downloading and piping remote scripts to a shell.
Audit Metadata