hyperframes-registry

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches registry metadata and installation manifests from the official HeyGen HyperFrames repository on GitHub. Evidence: curl -s https://raw.githubusercontent.com/heygen-com/hyperframes/main/registry/registry.json (SKILL.md, references/discovery.md).
  • [COMMAND_EXECUTION]: Uses the hyperframes command-line interface to add, lint, and preview compositions. Evidence: hyperframes add, hyperframes lint, hyperframes preview (SKILL.md, examples/add-block.md, examples/add-component.md).
  • [REMOTE_CODE_EXECUTION]: Facilitates the download and integration of remote HTML, CSS, and JavaScript components from a centralized registry into the user's local environment. It also references the GSAP library via CDN. Evidence: https://cdn.jsdelivr.net/npm/gsap@3.14.2/dist/gsap.min.js (references/demo-html-pattern.md).
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests and processes data from external JSON manifests. 1. Ingestion points: registry.json and registry-item.json (references/discovery.md). 2. Boundary markers: None. 3. Capability inventory: File system writes (hyperframes add), file reading, and JavaScript snippet merging. 4. Sanitization: No explicit sanitization of registry metadata is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 06:33 PM