runway-image

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFE
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill follows security best practices by instructing users to store API secrets in environment variables (RUNWAYML_API_SECRET) rather than hardcoding them within the scripts or prompts.
  • [EXTERNAL_DOWNLOADS]: Downloads are restricted to official Runway endpoints and user-defined allowlisted hosts. The provided implementation includes validation for HTTPS, public IP addresses, MIME types, file signatures, and maximum pixel dimensions to mitigate risks associated with untrusted remote content.
  • [DATA_EXFILTRATION]: Network activity is transparent and limited to the official Runway API and specified output destinations. There is no evidence of unauthorized data collection or transmission to third-party servers.
  • [COMMAND_EXECUTION]: The provided code examples use standard library functions for file system operations (creating directories, writing artifacts) and network requests, without spawning arbitrary sub-processes or executing unverified shell commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 01:51 PM
Security Audit — agent-trust-hub — runway-image