generating-tests-from-business-logic

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external business logic documents to generate executable test code, creating a surface for indirect prompt injection.
  • Ingestion points: Reads from 'path/to/refined_bl_document.md' in SKILL.md and refers to 'BDD/project_config.yaml'.
  • Boundary markers: Absent; the instructions do not include delimiters or warnings to ignore embedded instructions in the processed files.
  • Capability inventory: The skill utilizes 'Write', 'Edit', and 'Bash' tools, which allow for filesystem modifications.
  • Sanitization: No input validation or sanitization is performed on the extracted business rules before they are interpolated into code templates.
  • [COMMAND_EXECUTION]: The skill uses shell commands to manage directories and create files.
  • Evidence: Step 10 uses 'mkdir -p' and 'cat' redirection to create test directory structures and save generated test files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 08:12 PM