comps

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

• Third-party content exposure detected (medium risk: 0.30). The workflow ingests outsider-authored free text from user-supplied “company named in the user's request” (company lookup step 1) and then uses it to fetch/compute market data and build the report, so an attacker can try prompt-injection via the company/name input path.