bitlysis-ai-agents-llm

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill functions as a documentation and best-practices guide for AI agent development, containing no malicious instructions or suspicious code patterns.
  • [CREDENTIALS_UNSAFE]: Step 1 of the instructions explicitly forbids hardcoding API keys and demonstrates the correct use of environment variables for secret management.
  • [PROMPT_INJECTION]: The skill proactively identifies external data as a risk for prompt injection and instructs the user to sanitize or sandbox untrusted content.
  • [COMMAND_EXECUTION]: The skill references standard development tools such as pytest for running local evaluation tests, which is expected behavior for a technical development guide.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 06:32 AM