The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Python subprocess module to perform system and local tool operations. scripts/doctor.py executes networksetup on macOS to retrieve network service lists and proxy configurations (-listallnetworkservices, -getwebproxy, -getsecurewebproxy). scripts/start_wxdown_service.py runs a local service by executing a Python script located in a user-provided directory (--wxdown-dir).- [EXTERNAL_DOWNLOADS]: The scripts/download_urls.py script fetches article data from a remote endpoint (https://down.mptext.top/api/public/v1/download). This is the default API used for article extraction.- [PROMPT_INJECTION]: The skill ingests and processes untrusted article content from the web, creating a potential surface for indirect prompt injection. Ingestion points: scripts/download_urls.py saves article bodies (Markdown/HTML/JSON) from the network to the local filesystem. Boundary markers: Absent. Capability inventory: The skill can execute shell commands (subprocess in doctor.py, start_wxdown_service.py) and perform network requests (urllib.request in download_urls.py). Sanitization: scripts/download_urls.py sanitizes filenames using regex, but the article content itself is processed without specialized filtering for malicious instructions.

wechat-mp-batch-exporter