tongstock-cli

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

• Third-party content exposure detected (high risk: 0.70). The skill exposes and returns public third-party F10/company content (e.g., "公司公告", "公司报道") via the company-content CLI command and the /api/company/content endpoint, meaning the agent ingests untrusted public announcements/media reports as part of its workflow which could influence decisions.