runway-sdk-patterns
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows security best practices by explicitly instructing the agent to redact API secrets, signed URLs, and prompt/media contents from logs and telemetry.
- [SAFE]: It utilizes environment variables (e.g.,
RUNWAYML_API_SECRET) and a secret provider instead of hardcoding credentials. - [SAFE]: Instructions include clear boundaries for tool usage, advising against mutating production resources (create, cancel, delete, etc.) without explicit operator approval.
- [SAFE]: The skill includes documentation integrity checks using SHA-256 fingerprints to ensure that the implementation guidance matches the original official source.
- [SAFE]: All external links point to official RunwayML documentation (docs.dev.runwayml.com), which is a well-known service domain.
Audit Metadata