hyperframes-fx

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands using npx hyperframes to manage project components, lint files, and render video outputs.
  • [REMOTE_CODE_EXECUTION]: It uses npx to download and execute visual effect packages (slugs) from the NPM registry at runtime.
  • [EXTERNAL_DOWNLOADS]: Transitions, overlays, and UI blocks are fetched from external package repositories during the setup and installation phases.
  • [PROMPT_INJECTION]: The skill reads local index.html files to identify card templates and layout, which serves as a potential ingestion point for indirect prompt injection.
  • Ingestion points: Reads and parses <div class="card clip ..."> tags from the project's index.html file.
  • Boundary markers: Absent; the skill relies on the existing HTML structure.
  • Capability inventory: Shell command execution (npx) and modification of project files.
  • Sanitization: Absent; the logic directly uses parsed class names and tag order to determine selection and timing parameters.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 06:42 PM
Security Audit — agent-trust-hub — hyperframes-fx