prompt-engineer
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No critical security vulnerabilities or malicious patterns were identified. The skill is composed of markdown-based instructions and does not ship with executable code or unauthorized dependencies.
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface: The skill is designed to ingest and iterate upon user-provided prompt text (SKILL.md). It lacks explicit boundary markers or instructions to the agent to treat this input as untrusted data, which could allow embedded instructions in a user's prompt to influence the expert personas defined in the skill.
- [PROMPT_INJECTION]: Metadata and Claims: The examples.md file and README.md include claims regarding 95% accuracy and full HIPAA compliance for generated medical prompts. These represent deceptive metadata as an AI-driven prompt engineering process cannot autonomously guarantee regulatory compliance or diagnostic accuracy. Users should be advised to perform manual verification for high-stakes domains.
Audit Metadata