skills/zapier/connectors/runway/Gen Agent Trust Hub

runway

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The cli.js wrapper utility uses spawnSync to launch the connector's internal entry point (cli.ts or dist/cli.js). This is a platform-standard mechanism for ensuring compatibility across different Node.js environments and does not execute arbitrary user-supplied input.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with the official Runway API at api.dev.runwayml.com. It also references documentation and authentication tools from zapier.com. These are legitimate external resources necessary for the skill's primary function.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external media assets via HTTPS URLs or data URIs to perform generative tasks (e.g., upscaling or restyling). While this constitutes an untrusted data ingestion surface, the skill implements strict Zod input validation and lacks exploitable capabilities like local file system modifications or arbitrary network routing that could be abused via indirect injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 02:42 PM
Security Audit — agent-trust-hub — runway