agile-tdd
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains instructional content for standard software engineering practices and does not include any malicious code or data exfiltration patterns.
- [SAFE]: No evidence of prompt injection, obfuscation, or unauthorized remote code execution was found.
- [SAFE]: The skill possesses a surface for indirect prompt injection through the ingestion of user arguments and local source code, however, this is a standard risk for development tools. Evidence: 1. Ingestion points: $ARGUMENTS and source code analysis in SKILL.md; 2. Boundary markers: Absent; 3. Capability inventory: shell command execution (bun test); 4. Sanitization: Absent.
- [SAFE]: Tooling references (Bun, Faker) are appropriate for the skill's stated purpose in a development environment.
Audit Metadata