vertex-ai-media-master

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (SKILL.md and references/core-capabilities.md) explicitly ingests third-party media from Cloud Storage URIs (e.g., gs://bucket/competitor-ad.mp4 and Part.from_uri(...) examples) and sends that untrusted/user-provided content to models for analysis and asset generation, so such content could materially influence model outputs and downstream actions.