iblai-api-agent-safety
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill interacts exclusively with the vendor's official API (api.iblai.app). No external or untrusted domains are used for data transmission or command execution.
- [SAFE]: Authentication is managed via environment variables ($IBLAI_API_KEY, $IBLAI_ORG, $IBLAI_USERNAME), which is the recommended practice for secure credential handling in agent skills.
- [SAFE]: The skill's functionality is limited to managing agent safety parameters and auditing moderation logs, which aligns with its stated purpose of providing administrative controls for AI safety.
Audit Metadata