video-hyperframes
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill ingests untrusted user content to generate structured HTML frames.
- Ingestion points:
SKILL.mdinstructions process user content density to determine the number of frames and their content. - Boundary markers: Absent. There are no explicit delimiters or instructions for the agent to ignore embedded commands within the user's content.
- Capability inventory: The skill generates HTML and JavaScript meant for execution in a UI preview surface, which could be exploited if the injected content attempts to execute unauthorized scripts or exfiltrate data from the preview context.
- Sanitization: Absent. The instructions do not mandate escaping or filtering of the user-provided text before interpolation into the HTML templates.
Audit Metadata