wx-channels-download
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill communicates with a third-party parser endpoint (default: https://sph.litao.workers.dev) and subsequent media URLs to download video files. This is the primary function of the skill and is handled using standard libraries.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from user-provided URLs and remote service responses.
- Ingestion points: Input URLs provided to the CLI and JSON data received from the remote parser.
- Boundary markers: No explicit delimiters are used in the prompt instructions to isolate untrusted data from the agent context.
- Capability inventory: The script performs file system writes to save media and creates directories as needed. The agent workflow suggests verifying files using external tools like ffprobe if available.
- Sanitization: The script uses a strict regular expression to validate the WeChat share URL format before processing and includes a sanitization routine to remove unsafe characters from filenames generated from video descriptions.
Audit Metadata