test-case-generator

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a static prompt template for generating test cases based on user-supplied code or descriptions. No executable code or tools are invoked.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input which could contain instructions.
  • Ingestion points: The [PASTE CODE OR DESCRIBE THE FEATURE] placeholder in SKILL.md.
  • Boundary markers: The input is wrapped in <code_or_description> tags, which is a recommended practice to help the model distinguish between instructions and data.
  • Capability inventory: The skill does not use any tools (allowed-tools is empty/not specified) and does not perform file, network, or system operations.
  • Sanitization: No explicit sanitization is present, but the risk is minimal as the skill's only action is generating text for the user's review.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 01:00 AM
Security Audit — agent-trust-hub — test-case-generator