testing-best-practices
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFE
Full Analysis
- SAFE (SAFE): The skill consists exclusively of markdown-based instructions for the AI agent. There are no executable files, scripts, or package manager configurations that could pose a security risk.
- Indirect Prompt Injection (SAFE): The skill describes processes for reading external code and specification files (ingestion points). However, because the skill defines no tools or actions (capability inventory) such as network requests or command execution, it lacks an exploitation path for malicious content embedded in those files.
- PROMPT_INJECTION (SAFE): The instructions include a safety-positive constraint that directs the agent to follow system and project rules in the event of any conflict with the skill's instructions.
Audit Metadata