test-driven-development
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as an educational and procedural guide for software development, focusing on enforcing the TDD methodology without malicious intent.
- [SAFE]: No obfuscation, data exfiltration, or persistence mechanisms were detected in the provided files.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface common to developer tools that process external code.
- Ingestion points: User-authored source code and test files are ingested and processed during the development cycle described in
SKILL.md. - Boundary markers: The instructions do not specify delimiters or boundary markers for the user-provided code content.
- Capability inventory: The skill references the execution of shell commands (
npm test) to verify code behavior inSKILL.md. - Sanitization: There is no explicit sanitization, validation, or filtering of the user-provided code or the environment configuration (e.g.,
package.jsonscripts) before execution. - Note: This surface is expected for a development-focused skill and is documented here as an inherent risk of the tool's intended functionality.
Audit Metadata