alltuu-downloader

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires the agent to execute shell commands to configure the operating environment, specifically launching a Chrome Canary instance with the remote debugging port enabled and installing the necessary 'ws' Node.js library for WebSocket communication with the browser.
  • [EXTERNAL_DOWNLOADS]: The Node.js script connects to alltuu.com and its associated content delivery networks (CDNs) to download image files. This behavior is explicitly defined as the skill's primary purpose and involves no unauthorized data transfer.
  • [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection because it ingests and processes external data from a web API.
  • Ingestion points: The 'scripts/download.js' script uses Chrome CDP's Network.getResponseBody method to capture JSON data from the 'v4c.alltuu.com' domain.
  • Boundary markers: The script does not implement specific boundary markers or 'ignore' instructions for the external content, though the risk is mitigated by its specialized purpose.
  • Capability inventory: The script has permissions to create directories and write files to the user's Downloads folder.
  • Sanitization: The script uses a local naming template for files, though the file extension is determined by the remote URL path, which is typical for downloader utilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 01:22 PM