hyperframes
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches components from the official HeyGen GitHub repository (github.com/heygen-com/hyperframes) during its installation process.
- [COMMAND_EXECUTION]: The installation workflow involves executing shell commands including
git clone,npx skills add, andrm -rfto manage the skill files and registration. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided HTML and animation data to generate video, which represents a surface where untrusted data enters the agent context.
- Ingestion points: HTML composition files and timing data specified in DOM attributes (documented in SKILL.md).
- Boundary markers: No specific delimiters or warnings for embedded instructions are mentioned in the provided stubs.
- Capability inventory: Performs file system operations for video rendering, executes ffmpeg for encoding, and accesses network APIs for cloud-based media features (documented in SKILL.md).
- Sanitization: Processing relies on established animation runtimes such as GSAP, Anime.js, and Three.js.
Audit Metadata