paw-cra-video-longform

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The skill searches and fetches media from Pexels API and fal.ai API during scene generation and B-roll integration, which can contain outsider-authored text/metadata, presenting a low prompt injection risk.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill references external API endpoints (https://queue.fal.run, https://api.pexels.com, https://api.elevenlabs.io) used during runtime for content generation, establishing a weak/unknown/suspicious operational dependency because their provenance is unauthenticated third-party services.