openai-rag-runtime
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill explicitly identifies retrieved content as untrusted input and mandates the implementation of prompt-injection defenses.
- [SAFE]: Operating rules strictly prohibit the leakage of PII or secrets through prompts, retrieved context, or telemetry logs.
- [SAFE]: No external dependencies, remote script executions, or network operations to untrusted domains were identified.
- [SAFE]: All references to standards and other skills are local file paths, ensuring no external code injection via the reference mechanism.
Audit Metadata