The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses bash -c to execute shell commands that interact with the Wix API. This is the primary mechanism for the skill's functionality.
[EXTERNAL_DOWNLOADS]: The skill connects to https://www.wixapis.com, which is the official REST API for Wix, a well-known and trusted service.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it processes data (contacts, blog posts, orders) fetched from an external API.
Ingestion points: Wix API response data processed in multiple sections of SKILL.md.
Boundary markers: No specific boundary markers or instructions are provided to the agent to ignore embedded instructions in the retrieved data.
Capability inventory: The skill possesses network access capabilities via curl, local file write capabilities to /tmp/request.json, and general command execution via bash and jq.
Sanitization: The skill uses jq to parse specific fields from JSON responses, which provides structure but does not sanitize the text content for potential malicious instructions.

wix