cartoon-ad
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a robust workflow for creative media production and does not contain any detected security threats or malicious code components. All referenced capabilities such as $video-analysis and $image-batch-runner are treated as internal platform tool calls.
- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates awareness of the risks associated with processing user-supplied data, specifically by establishing strict 'Claim Boundaries' that prohibit the agent from inventing medical, performance, or financial claims not present in the source context. While the skill ingests external briefs and video files, these quality controls act as effective guardrails for the agent's output by restricting the generation of unverified information.
Audit Metadata