generate-test-cases

Pass

Audited by Gen Agent Trust Hub on Oct 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONPERSISTENCE
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on executing local Python scripts to perform its core functions. It calls scripts/generate_xmind.py to convert JSON-formatted test cases into XMind files and scripts/memory_manager.py to handle the persistence and retrieval of project-specific context and learning data.
  • [PERSISTENCE]: The skill implements a self-learning mechanism by maintaining a .memory/ directory. It stores project context, terminology, generation history, user preferences, and decision records across sessions to improve future generation results. This allows the skill to persist data and influence its own behavior over time based on previously processed information.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which creates a vulnerability surface for indirect prompt injection.
  • Ingestion points: The skill reads all Markdown files (.md) and various image formats (.png, .jpg, .jpeg, .gif, .webp, .bmp, .svg) located in the requirements/ directory.
  • Boundary markers: The workflow uses basic --- separators between files but lacks explicit instructions to ignore or treat embedded commands within the requirement documents as untrusted data.
  • Capability inventory: The skill has the ability to execute shell commands (via python3), write to the file system (in tmp/, .memory/, and test-docs/), and update its internal memory system based on the processed data.
  • Sanitization: There is no explicit mention of sanitizing or escaping the content extracted from the requirement files before it is processed by the AI or stored in the persistence layer.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 14, 2026, 10:19 AM