video
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains standard instructions and examples for creating video content using reputable tools such as HeyGen, Remotion, and Hyperframes. No malicious code or exfiltration patterns were detected.- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for ingesting local marketing context files, which is a standard procedure for tailoring AI responses to specific business needs.
- Ingestion points: Reads
.agents/product-marketing.md,.claude/product-marketing.md, orproduct-marketing-context.md(SKILL.md). - Boundary markers: None specified in the instructions.
- Capability inventory: Supports package installation via NPM and programmatic video code generation (SKILL.md).
- Sanitization: None; the skill treats local marketing context files as trusted local inputs.
Audit Metadata