hyperframes-cli

Pass

Audited by Gen Agent Trust Hub on Jun 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on shell commands via npx hyperframes to perform its primary functions, including project initialization, rendering, and environment diagnostics.
  • [EXTERNAL_DOWNLOADS]: Executing npx hyperframes involves downloading the package from the npm registry. The upgrade command also implies network connectivity for version management.
  • [DATA_EXFILTRATION]: The skill facilitates the upload of rendered video files to Supabase storage. This is a functional requirement to provide the user with playable media links and is conducted through a trusted service.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing user-provided content.
  • Ingestion points: The skill ingests HTML compositions and media files (MP3, MP4) provided by the user for rendering and transcription tasks as seen in SKILL.md.
  • Boundary markers: No explicit instruction delimiters or guidelines are provided to the agent for handling user-supplied data within processed files.
  • Capability inventory: The environment allows for shell command execution (npx), file system access to artifacts, and network egress for storage uploads.
  • Sanitization: The instructions do not document any sanitization or validation of the processed HTML or media files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 9, 2026, 09:35 PM
Security Audit — agent-trust-hub — hyperframes-cli