website-to-hyperframes

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill incorporates external libraries and components from JSDelivr, including GSAP (MotionPathPlugin) and the DotLottie player, which are standard tools for web-based animation and vector playback.
  • [COMMAND_EXECUTION]: The workflow relies on npx to execute hyperframes and tsx for core operations such as site capture, linting, validation, and rendering. These are functional requirements for the framework's operation.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted text and metadata from user-provided URLs.
  • Ingestion points: Content is extracted from websites into tokens.json and visible-text.txt using the capture command.
  • Boundary markers: The instructions do not explicitly mandate delimiters or 'ignore' instructions for the agent when processing the extracted text.
  • Capability inventory: The agent can perform file writes, execute shell commands via npx, and delegate tasks to sub-agents.
  • Sanitization: There is no documented process for sanitizing or escaping the captured web content before it is used to generate scripts or narration.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 07:31 AM
Security Audit — agent-trust-hub — website-to-hyperframes