Agent-Media UGC Video
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns such as prompt injection, data exfiltration, or obfuscation were detected. The skill correctly uses environment variables for API keys and targets the vendor's official API domains.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted text via the
scriptparameter to generate video content. While this represents a data ingestion surface, the risk is localized to the generated media output and does not grant the skill unauthorized access to the host system or sensitive data. Boundary markers are managed by the underlying tool logic.
Audit Metadata