assessment-orchestrator

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow performs active discovery (e.g., discover-components.sh using subdomain_enumeration, link_parsing, openapi_discovery with tools like curl/httpx/katana), which can fetch and ingest outsider-authored free text from public web resources and arbitrary external URLs into the LLM context via the discovered component outputs.