openai-agents
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [EXTERNAL_DOWNLOADS] (LOW): The skill instructions and README reference '@openai/agents' and 'zod'. OpenAI is categorized as a trusted source under the [TRUST-SCOPE-RULE], and zod is a standard industry library for schema validation.
- [CREDENTIALS_UNSAFE] (SAFE): While the 'Quick Start' section mentions 'OPENAI_API_KEY', it uses a placeholder value ('your-key') and follows best practices by suggesting the use of environment variables rather than hardcoding secrets.
- [PROMPT_INJECTION] (SAFE): The extensive list of keywords and triggers are intended for skill activation and context matching. No malicious 'ignore previous instructions' or bypass commands were detected.
- [REMOTE_CODE_EXECUTION] (SAFE): The skill contains no code that downloads or executes scripts from untrusted remote locations. All mentioned packages are from verified registries.
Audit Metadata