byted-marketing-agent-trending-list

Warn

Audited by Gen Agent Trust Hub on Mar 26, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to modify the host system by running 'apt update && apt install python3-venv -y'. This requires elevated privileges and changes the system-wide state to satisfy software dependencies.\n- [EXTERNAL_DOWNLOADS]: The environment setup process involves downloading and installing the 'volcengine-python-sdk' package via pip. This is a legitimate dependency provided by the vendor (Bytedance) for accessing their cloud APIs.\n- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface (Category 8) by ingesting external data from Volcengine APIs.\n
  • Ingestion points: API results containing trending topic descriptions, event summaries, and analysis content (file: openapi_client.py).\n
  • Boundary markers: Data is presented within Markdown tables and sections in the instructions, but lacks explicit delimiters or instructions to ignore embedded commands.\n
  • Capability inventory: The skill environment allows shell execution (bash) and Python script execution, providing a pathway if the agent is influenced by malicious data.\n
  • Sanitization: The script performs key-based filtering but does not sanitize or escape the content of the data fields before passing them to the agent context.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 26, 2026, 03:03 PM