hyperframes

Pass

Audited by Gen Agent Trust Hub on Jul 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references and suggests installing additional workflows from the heygen-com/hyperframes repository. This originates from a well-known technology service.
  • [COMMAND_EXECUTION]: The skill instructions involve executing commands via npx for rendering, linting, and project management. It also utilizes the GitHub CLI (gh) to retrieve pull request information for video content generation.
  • [PROMPT_INJECTION]: The skill is designed to process untrusted data from external sources such as URLs and GitHub pull requests, creating a surface for indirect injection. Evidence: 1. Ingestion points: GitHub PR URLs and website content (SKILL.md). 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the routing logic. 3. Capability inventory: Use of CLI tools including npx and gh for data retrieval and processing. 4. Sanitization: No explicit sanitization or filtering of external content is described in this routing skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 4, 2026, 11:53 AM
Security Audit — agent-trust-hub — hyperframes