existing-repo
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands such as
git log,find, andgrepto analyze repository structure and detect coding conventions. - [COMMAND_EXECUTION]: The skill generates configuration files and shell scripts, using
chmod +xto make Husky hooks executable. - [EXTERNAL_DOWNLOADS]: The skill installs software packages via
npmandpip, including industry-standard tools for linting, formatting, and pre-commit management. - [REMOTE_CODE_EXECUTION]: The skill sets up a pre-commit framework that downloads and executes scripts from established GitHub repositories for tasks like linting and security scanning.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing untrusted repository data.
- Ingestion points: Reads repository files including
package.json,README.md, and git history (SKILL.md). - Boundary markers: Lacks delimiters or instructions to ignore embedded commands in the processed files.
- Capability inventory: Employs
Bashfor file modification and tool installation. - Sanitization: Performs no sanitization of file content before analysis.
Audit Metadata