explainer-video-production
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown and evaluation criteria. It contains no executable code, remote script downloads, or obfuscated content. All external links point to trusted organizations and well-known services (W3C, FTC, CDC, U.S. Government).
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for transforming untrusted user-supplied data (briefs, research, datasets) into structured video plans. It includes robust built-in controls to mitigate the risk of processing malicious instructions or generating misinformation.
- Ingestion points: Processes user-provided topics, research corpora, and product briefs as described in the 'Intake' section of SKILL.md.
- Boundary markers: Enforces the separation of documented facts from source-backed inferences and creative inventions to maintain context boundaries.
- Capability inventory: The skill enables the agent to generate narration, storyboards, and prompts for media generation tools, but prohibits the generation of factual charts or legal/medical text via non-deterministic means.
- Sanitization: Implements a mandatory 'Claim Matrix' for source verification and an 'Escalation' protocol requiring human review for high-risk domains such as health, law, safety, and finance.
Audit Metadata