title-sequence-3d
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided text for scene descriptions and titles which are interpolated directly into a prompt template used for code generation without sanitization.
- Ingestion points: User inputs for the landing line, world setting, and accent words defined in Step 1 and Step 2.
- Boundary markers: Absent. The prompt template in Step 2 uses simple placeholders (e.g., [LINE], [WORLD]) without delimiters or instructions to the agent to treat the content as potentially untrusted data.
- Capability inventory: The agent is tasked with generating executable web code (index.html) and providing instructions for external tool execution via npx.
- Sanitization: No sanitization or validation of the user-provided strings is performed before they are processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the heygen-com/hyperframes utility via npx. This tool is provided by a well-known AI video service provider.
Audit Metadata