tdd
Pass
Audited by Gen Agent Trust Hub on May 7, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands (
git checkout,pnpm test:coverage,vitest) to verify code changes and coverage metrics. This introduces an indirect prompt injection surface common to development tools. - Ingestion points: Project source code, branch names, and
package.jsonscript definitions referenced inSKILL.md. - Boundary markers: Absent; the instructions do not include specific warnings to verify script content before execution.
- Capability inventory: Local shell execution for version control and test running via
pnpmas described inSKILL.md. - Sanitization: Absent; the agent is expected to run scripts provided by the development environment.
- [SAFE]: No malicious obfuscation, credential harvesting, or unauthorized network operations were detected. The skill aligns with standard software engineering practices.
Audit Metadata