The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of an external Python package named miku_ai using pip install miku_ai --break-system-packages. This package is not provided by a recognized trusted vendor, and its security posture is unverified.
[COMMAND_EXECUTION]: The skill provides a Python script designed to be executed via python3 -c. This script imports the miku_ai library and performs network operations to interact with WeChat's search interface.
[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from the internet in the form of WeChat article titles and digests.
Ingestion points: Data returned by the get_wexin_article function (SKILL.md).
Boundary markers: No specific delimiters or "ignore instructions" warnings are present in the provided logic to separate article content from agent instructions.
Capability inventory: The skill environment has capabilities for shell command execution (python3 -c) and package installation (pip).
Sanitization: There is no evidence of sanitization, filtering, or escaping of the external article content before it is processed by the agent or presented to the user.

wechat-search