doc-flow-diagram-generator

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and crawls public documentation pages (scripts/single_page_parser.py and scripts/doc_crawler.py) and ingests that untrusted third‑party website content as part of its required flow-detection workflow, so arbitrary webpage instructions could influence the agent's analysis and generated actions.