The Agent Skills Directory

[CREDENTIALS_UNSAFE]: An example API key (ak_c4fc9018ffb14ce4ae35dafd92f466c3) is hardcoded in the documentation file references/gzh_trend_data_format.md. While this appears to be for illustrative purposes, hardcoding any credential is a best practice violation.\n- [EXTERNAL_DOWNLOADS]: The skill communicates with https://redfox.hk to retrieve search results, which is the functional endpoint for the service provided by the vendor redfox-data.\n- [COMMAND_EXECUTION]: Executes the local script scripts/fetch_gzh_trends.py to handle data retrieval and formatting.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) due to processing untrusted data.\n
Ingestion points: The skill fetches and displays article titles and summaries from external WeChat sources via the RedFox API.\n
Boundary markers: No specific delimiters or safety instructions are used when presenting the fetched article data to the user.\n
Capability inventory: The skill can execute local Python scripts and has access to the calendar_create tool for managing subscriptions.\n
Sanitization: There is no evidence of sanitization or filtering applied to the external content before it is processed by the agent.

wechat-search