runware-run

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill documents standard integration patterns for the Runware platform.
  • [EXTERNAL_DOWNLOADS]: Mentions official vendor-distributed packages: the TypeScript SDK (@runware/sdk) and Python SDK (runware). These are verified vendor resources from 'runware'.
  • [DATA_EXFILTRATION]: Directs the agent to send task data to the official Runware endpoint (api.runware.ai/v1). No unauthorized data exfiltration or credential leaks were found.
  • [PROMPT_INJECTION]: No instructions were found that attempt to bypass AI safety guidelines or override system behavior.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing user-supplied data (prompts and media) for API submission. This is the intended primary purpose of the skill and follows standard API interaction patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 04:07 PM
Security Audit — agent-trust-hub — runware-run