agency-prompt-engineer
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides educational content and templates for prompt engineering. All code examples are for illustrative purposes and target common development tasks like building few-shot examples or running tests with standard libraries. The prompt injection patterns flagged by automated tools are found within a test suite template (
"Ignore instructions", "refuses gracefully", "edge: prompt injection") meant to prevent or test for injection, not to execute it. No remote downloads, exfiltration, or malicious commands were detected.
Audit Metadata