hyperframes

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the HyperFrames CLI tool using npx. This download originates from the npm registry and is associated with HeyGen, a well-known service in the AI video generation domain.\n- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as npx hyperframes install and npx hyperframes create. these are intended for setting up the environment and creating video project templates.\n- [PROMPT_INJECTION]: The skill's primary function involves reading and editing HTML, CSS, and JavaScript composition files, which presents a surface for indirect prompt injection. Malicious instructions could be embedded in these data files to influence the agent's editing decisions.\n
  • Ingestion points: Composition files (e.g., product-promo.html) read by the agent from the local filesystem.\n
  • Boundary markers: No specific delimiters or safety instructions are present to distinguish between data and potentially malicious embedded commands within the composition files.\n
  • Capability inventory: The agent has the ability to execute shell commands (npx) and perform file system writes.\n
  • Sanitization: There is no evidence of sanitization or validation of the input composition content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 05:22 AM
Security Audit — agent-trust-hub — hyperframes