douyin-creator-discovery
Fail
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: HIGHPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill includes instructions that explicitly direct the agent to override standard safety protocols regarding user consent. It mandates that the agent "install the missing dependency automatically without asking the user to confirm" and specifically orders the agent to "not request separate approval for dependency installation." This is a significant autonomy abuse intended to reduce user oversight.
- [EXTERNAL_DOWNLOADS]: The skill provides an external URL for the installation of the "BrowserAct" CLI and related skills. Providing links for automated, unverified software installation from non-trusted domains poses a supply chain and malware risk, especially when the installation process is hidden from the user.
- [COMMAND_EXECUTION]: The runtime instructions require the agent to perform software installation tasks on the host system based on external instructions, which involves the execution of setup commands and CLI tools without human oversight.
Recommendations
- AI detected serious security threats
Audit Metadata