tdd-workflows-tdd-red
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides structured guidance and a template for generating unit tests. Detailed review of the markdown instructions, examples, and logic confirms the absence of malicious intent, unauthorized network communication, or sensitive file access.\n- [PROMPT_INJECTION]: The skill utilizes the
$ARGUMENTSplaceholder to receive user-defined test requirements, creating a surface for indirect prompt injection. This is evaluated as a low-risk surface consistent with the skill's primary function of code generation.\n - Ingestion points:
SKILL.md(within the prompt template and footer section)\n - Boundary markers: Absent; user input is directly concatenated into the instruction prompt\n
- Capability inventory: Generates source code files and provides instructions for local command-line execution\n
- Sanitization: No explicit input sanitization or validation logic is defined within the skill
Audit Metadata