skills/runwayml/skills/runway-dev/Gen Agent Trust Hub

runway-dev

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches documentation and integration metadata from the author's official developer domain (docs.dev.runwayml.com).
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external documentation (llms.txt) and live tool output (MCP list_models) to guide code generation.
  • Ingestion points: SKILL.md refers to https://docs.dev.runwayml.com/llms.txt and tool outputs from the runwayml MCP server.
  • Boundary markers: Absent.
  • Capability inventory: SDK installation, file system modification (integration into projects), and network communication via the Runway SDK.
  • Sanitization: Not specified; the skill relies on following instructions provided by the official documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 07:15 PM
Security Audit — agent-trust-hub — runway-dev