douyin-video-extractor

Fail

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches the uv package manager installer from the official astral.sh domain and clones the project repository from GitHub.
  • [REMOTE_CODE_EXECUTION]: The installation process involves downloading a shell script from astral.sh and executing it directly via a pipe to sh.
  • [COMMAND_EXECUTION]: Executes shell commands to install system dependencies (ffmpeg), manage the Python environment (uv), and run the application components.
  • [DYNAMIC_EXECUTION]: Uses uv run and uvx to dynamically execute Python scripts and the MCP server at runtime.
  • [INDIRECT_PROMPT_INJECTION]: Processes untrusted data from external video platforms (Douyin/TikTok), specifically video titles and audio transcriptions.
  • Ingestion points: Video metadata and audio transcripts ingested via the parse_douyin_video_info and extract_douyin_text tools in SKILL.md.
  • Boundary markers: Absent; the skill does not explicitly instruct the agent to treat extracted text as untrusted or ignore potential instructions within it.
  • Capability inventory: File system writes (save_markdown, download_video), network requests, and script execution (uv run).
  • Sanitization: Absent; the transcription and metadata are presented to the agent without filtering or escaping.
Recommendations
  • HIGH: Downloads and executes remote code from: https://astral.sh/uv/install.sh - DO NOT USE without thorough review
Audit Metadata
Risk Level
HIGH
Analyzed
Sep 16, 2026, 10:44 PM
Security Audit — agent-trust-hub — douyin-video-extractor