hyperframes-creative

Warn

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: MEDIUMREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill uses a custom utility in scripts/package-loader.mjs to automatically install missing Node.js dependencies (such as sharp and @hyperframes/producer) using npm install at runtime. While it includes the --ignore-scripts flag to prevent post-install scripts from running, this pattern still introduces external code into the execution environment dynamically.
  • [COMMAND_EXECUTION]:
  • The script scripts/extract-audio-data.py uses subprocess.run to execute the ffmpeg command-line tool for audio processing.
  • The documentation in references/design-picker.md instructs the AI agent to start a background HTTP server using python3 -m http.server. This exposes the project directory on the local network, which may be unintended depending on the deployment environment.
  • [DYNAMIC_EXECUTION]: The scripts/package-loader.mjs utility uses spawnSync to re-spawn the current Node.js process with a modified environment (augmented PATH) after completing its automated dependency installation.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary workflow, described in references/prompt-expansion.md, involves ingesting untrusted user prompts and expanding them into detailed scene-by-scene instructions for sub-agents.
  • Ingestion points: Untrusted user input enters the context during the initial project prompt stage.
  • Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore embedded instructions within user content.
  • Capability inventory: The skill can execute shell commands, manage its own Node.js environment, and start network servers.
  • Sanitization: There are no explicit sanitization or validation steps before user input is expanded and processed by other automated tasks.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 14, 2026, 08:43 AM