The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes article titles and summaries fetched from an external API (redfox.hk). This content is untrusted and could contain malicious instructions designed to influence the agent's behavior during article generation.
Ingestion points: scripts/fetch_gzh_trends.py fetches article data from the RedFox API.
Boundary markers: No explicit boundary markers or "ignore instructions" warnings are used when processing the fetched content.
Capability inventory: The skill can execute shell commands (alipay-bot), run Python scripts (scripts/fetch_gzh_trends.py), and perform web searches.
Sanitization: No sanitization or validation of the fetched article content is implemented before it is used in the prompt for article generation.
[EXTERNAL_DOWNLOADS]: The skill instructions include installing the @alipay/agent-payment package from the official NPM registry using npx. This is a well-known service used for the skill's payment functionality.
[COMMAND_EXECUTION]: The skill executes local Python scripts to fetch data and utilizes the alipay-bot CLI for payment-related operations. These are documented as part of the skill's core functionality.

wechat-write