douyin-prohibited-word
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill extracts content from user-provided websites and files. This untrusted data is then processed by the agent to generate replacement suggestions and optimized copy, creating a surface where malicious instructions embedded in the source content could attempt to influence the agent's behavior.
- [EXTERNAL_DOWNLOADS]: The skill performs downloads during its setup and operation, including the installation of the
alipay-botutility vianpxfor payment handling and the Chromium browser viaplaywrightfor web scraping. These downloads target well-known and established service providers. - [COMMAND_EXECUTION]: The skill executes local Python scripts and the
alipay-botcommand-line interface to perform its core functions, including text extraction, API communication, and status polling for payments. These executions are constrained to the skill's documented workflows.
Audit Metadata