ocr

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly shows ingesting arbitrary external documents via the --document-url flag (e.g., "casedev ocr process --document-url ..."), meaning the agent fetches and reads untrusted public URLs and will interpret their text as part of its workflow, enabling indirect prompt injection.