The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses standard command-line utilities including curl, jq, and cat to facilitate communication with Wix API endpoints and handle JSON data. These operations target the official wixapis.com domain.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it retrieves content from an external platform that is then processed by the agent.
Ingestion points: Data is ingested from the Wix API (e.g., blog posts, contact info) via curl operations in SKILL.md.
Boundary markers: The skill does not employ specific delimiters or instructions to the agent to treat the retrieved API data as untrusted or to ignore any embedded instructions.
Capability inventory: The skill possesses network access via curl and the ability to write temporary files to /tmp using cat.
Sanitization: While the skill uses jq to filter specific JSON fields (e.g., ID, name, email), it does not perform escaping or validation of the text content within those fields before it enters the agent's context.

wix