hyperframes-registry

Pass

Audited by Gen Agent Trust Hub on Sep 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill makes extensive use of shell commands to manage project components, including hyperframes add, curl, npx, git, and gh.
  • [EXTERNAL_DOWNLOADS]: The skill fetches registry manifests and code snippets from HeyGen's official GitHub repository at https://raw.githubusercontent.com/heygen-com/hyperframes/main/registry.
  • [REMOTE_CODE_EXECUTION]: The hyperframes add command downloads external HTML, CSS, and JavaScript snippets and writes them to the local filesystem to be integrated into the project's execution environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes data from an external registry.
  • Ingestion points: Remote registry manifest (registry.json) and component files loaded via hyperframes add and curl (referenced in SKILL.md and references/discovery.md).
  • Boundary markers: Absent; the skill does not use delimiters or warnings to ignore instructions within registry content.
  • Capability inventory: Shell command execution (SKILL.md), network access, and local file writing (hyperframes add).
  • Sanitization: Absent; no validation or sanitization of the downloaded registry content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 26, 2026, 07:50 PM