The Agent Skills Directory

[PROMPT_INJECTION]: The skill ingests untrusted data from migration artifacts which creates a surface for indirect prompt injection. 1. Ingestion points: migrations//source-schema.json and migrations//source-profile.md. 2. Boundary markers: None specified. 3. Capability inventory: Reading and writing files within the project directory and verifying schemas via the Wix MCP tool. 4. Sanitization: No explicit sanitization or filtering of input content is defined. 5. Assessment: As this is a standard requirement for the skill's purpose, it is classified as safe.
[EXTERNAL_DOWNLOADS]: The documentation reference file wix-business-solutions-taxonomy.md contains links to official Wix API documentation at dev.wix.com. These are legitimate references to well-known service documentation and do not pose a risk.

rp-mapper