replatform

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). In the replatform runtime pipeline, the agent runs rp-discovery which “inspects the source system” starting from a user-supplied source URL/acquisition mode and then hands discovered content forward via generated source-schema.json/source-profile.md artifacts (LLM ingests mappings/review artifacts derived from that captured content).

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs running remote installer/CLI commands that fetch and execute third‑party code at runtime (e.g. "npm create @wix/new@latest -- headless" and "npx @wix/cli@latest token --site "$WIX_SITE_ID""), which are required for site creation/token minting and therefore represent runtime execution of external code.