The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes event details provided by the user (content, address, and WeChat contact) which are then interpolated into API requests. This represents a potential surface for indirect prompt injection.
Ingestion points: The skill collects information through user dialogue as described in the steps within SKILL.md and SKILL_cn.md.
Boundary markers: There are no explicit instructions or delimiters used to isolate user-provided text from the API request structure.
Capability inventory: The agent is instructed to use fetch to call https://api.fore.vip/mcp/create_activity and to navigate to the resulting activity URL.
Sanitization: The skill documentation describes basic validation for length and presence but does not include instructions for content sanitization or escaping.
[EXTERNAL_DOWNLOADS]: The documentation provides links to download a Chrome extension ZIP file from the vendor's domain (f.fore.vip). This is an official companion tool for the platform.
[DATA_EXFILTRATION]: The skill transmits user-provided event information and contact details (WeChat ID) to the vendor-controlled API endpoint api.fore.vip. This is the intended primary function of the skill.
[COMMAND_EXECUTION]: The provided test_local.sh script uses the curl command to interact with the vendor's API for testing purposes.

activity-create