hyperframes

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions for the agent to install and update specialized video and animation sub-skills from the heygen-com/hyperframes repository on GitHub. These operations use the npx package runner and target a well-known technology provider, representing legitimate functional dependencies within the framework.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines workflows that ingest data from external, potentially untrusted sources to inform video generation, which creates a vulnerability surface for indirect prompt injection. Ingestion points: Website URLs (crawled for assets and brand tokens) and GitHub Pull Requests (read via the gh CLI) are used as inputs for various video workflows. Boundary markers: None are explicitly defined in this routing skill; delimitation is expected to be handled by the specialized domain skills to which requests are routed. Capability inventory: Capabilities include headless browser crawling, local transcription via Whisper, and interaction with the GitHub CLI. Sanitization: No specific sanitization or filtering logic for ingested content is described in the routing documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 12:02 AM