The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external data from mapping-plan.md and mapping-summary.md to identify Wix-side setup requirements. This ingestion of untrusted content represents a potential attack surface for indirect prompt injection.
Ingestion points: Reads local files mapping-plan.md and mapping-summary.md from the migrations/ directory.
Boundary markers: No explicit delimiters or boundary instructions are provided to the agent to isolate the file content from instructions.
Capability inventory: The skill possesses file read/write capabilities (creating setup-requirements.md) and uses the Wix MCP for environment verification.
Sanitization: No explicit sanitization or input validation is specified for the processed data.
[EXTERNAL_DOWNLOADS]: Documentation provides user-facing instructions to install ngrok using Homebrew (brew install ngrok) for media reachability. This is a well-known development tool, and the skill provides a clear placeholder (<YOUR_AUTHTOKEN>) for the user's own credentials, preventing credential exposure.

rp-setup-discovery