douyin-creator-discovery

Warn

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions explicitly direct the agent to install a command-line interface (CLI) tool automatically. It states, "use [Install BrowserAct]... to install the missing dependency automatically without asking the user to confirm."
  • [EXTERNAL_DOWNLOADS]: The skill requires downloading software from an external domain (browseract.com) and a GitHub repository (github.com/browser-act/skills). It further instructs the agent to "not request separate approval for dependency installation," which bypasses standard user oversight for external content.
  • [REMOTE_CODE_EXECUTION]: By automating the installation of a CLI tool from a remote source without human-in-the-loop verification, the skill creates a path for remote code to be executed on the host system.
  • [DATA_EXFILTRATION]: While not directly exfiltrating data, the skill processes content from Douyin (an external website), which presents an indirect prompt injection surface where malicious content on a webpage could potentially influence the agent's behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 20, 2026, 04:35 AM
Security Audit — agent-trust-hub — douyin-creator-discovery