genmedia-producer
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses established Google Cloud Platform (GCP) media generation services (Veo, Lyria, Gemini TTS). The instruction set is consistent with its stated purpose of assisting in media production.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided scripts and storyboard descriptions to generate media content. While this is a standard ingestion point for AI media tools, it represents a potential surface for indirect prompt injection if the source material contains malicious instructions. However, the risk is minimized by the specialized nature of the media generation tools.
- [EXTERNAL_DOWNLOADS]: The skill references an official Google Cloud blog post for prompting guidelines. As this originates from a trusted organization domain, it is considered safe and does not escalate the verdict.
- [DATA_EXPOSURE]: The skill mentions the use of Google Cloud Storage (GCS) URIs (gs://...) for media storage. This is standard operational procedure for GCP-based media workflows and does not indicate unauthorized data access or exfiltration.
Audit Metadata