prompt-engineer
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides documentation on prompt design, optimization, and security best practices.
- [SAFE]: Mentioned prompt injection patterns (e.g., 'ignore previous instructions') are found within educational tables describing attack vectors for the purpose of implementing defenses. This is instructional content and does not represent a malicious attempt to inject instructions.
- [SAFE]: Code snippets provided are implementation templates for agents, guardrails, and observability. They utilize well-known and legitimate libraries.
- [SAFE]: The skill includes an example of insecure code (using
exec()) specifically for use in a code-review exercise for the AI, which is standard for the documented purpose of prompt testing.
Audit Metadata