omh-llm-app-dev
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a documentation-based workflow for LLM application development, containing architectural guidance rather than executable scripts.
- [SAFE]: It explicitly mandates the protection of sensitive data by forbidding the use of hardcoded credentials and requiring the use of environment variables or secret stores.
- [SAFE]: It provides proactive defenses against prompt injection by instructing developers to separate instruction channels from untrusted data (e.g., retrieved documents or user input).
- [SAFE]: All references to network tools like 'curl' or 'wget' are descriptive examples of implementation details for the developer to follow in their own code, and do not represent active commands executed by the agent.
- [SAFE]: No obfuscation, persistence mechanisms, or unauthorized privilege escalation attempts were detected in the files.
Audit Metadata