hyperframes-registry

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches registry manifests and component data from the official heygen-com GitHub organization, which is a well-known service.
  • [COMMAND_EXECUTION]: Instructs the agent to execute standard CLI tools (hyperframes, curl) for project initialization, component installation, and composition previewing.
  • [PROMPT_INJECTION]: The skill establishes an indirect prompt injection surface as it requires the agent to read and process external HTML and JavaScript snippets from a remote registry.
  • Ingestion points: The agent is instructed to read contents of files installed via hyperframes add (e.g., compositions/components/shimmer-sweep.html).
  • Boundary markers: No delimiters or specific instructions are provided to the agent to distinguish between its instructions and the content of the downloaded files.
  • Capability inventory: The agent has access to file system operations and shell command execution (hyperframes lint, hyperframes preview).
  • Sanitization: There is no indication of content validation or sanitization before the agent integrates the code snippets into the host composition.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 07:11 PM
Security Audit — agent-trust-hub — hyperframes-registry