cohere-hello-world

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or behaviors were identified in the skill instructions or code examples. The skill serves as a legitimate resource for developers.
  • [EXTERNAL_DOWNLOADS]: The skill references the official 'cohere-ai' and 'cohere' packages, which are standard libraries provided by Cohere for API integration.
  • [CREDENTIALS_UNSAFE]: Promotes secure handling of secrets by instructing users to use environment variables (CO_API_KEY) rather than hardcoding sensitive credentials.
  • [PROMPT_INJECTION]: The skill trigger phrases and instructional content are functional and do not attempt to override AI safety guidelines or manipulate agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 01:17 AM
Security Audit — agent-trust-hub — cohere-hello-world