skills/wix/skills/rp-execute-setup/Gen Agent Trust Hub

rp-execute-setup

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes configuration and requirement data from setup-requirements.md to automate environment provisioning, introducing an indirect prompt injection surface.
  • Ingestion points: Reads and interprets migration requirements from migrations/<project>/setup-requirements.md.
  • Boundary markers: No explicit delimiters or boundary instructions are defined to separate untrusted data from the agent's internal logic.
  • Capability inventory: The agent has the capability to perform site-wide administrative actions via CallWixSiteAPI, including installing Wix apps and creating database collections.
  • Sanitization: Lacks formal input validation or sanitization logic for the data extracted from the requirement artifacts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 06:44 AM
Security Audit — agent-trust-hub — rp-execute-setup