test-design-techniques

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides legitimate testing guidelines and does not contain any detected malicious instructions, obfuscation, or data exfiltration logic.
  • [NO_CODE]: No executable scripts or binary files are included in the skill package; it relies on markdown, JSON, and YAML for instruction and configuration.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes external natural language inputs to generate test scenarios.
  • Ingestion points: Inputs such as 'requirement', 'workflow', and 'rules' in 'evals/test-design-techniques.yaml' and 'SKILL.md'.
  • Boundary markers: No delimiters or explicit instructions to ignore embedded commands are present in the processing logic.
  • Capability inventory: Orchestrates specialized agents like 'qe-test-generator' via the 'FleetManager' coordination framework.
  • Sanitization: No sanitization, escaping, or schema validation for natural language input text is defined in the provided skill files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 09:25 AM