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 explicitly ingests and analyzes external, potentially untrusted media via Cloud Storage URIs (e.g., gs://bucket/... shown in SKILL.md and references/examples.md using Part.from_uri and model.generate_content), so third-party content can materially influence the agent's actions and outputs.