agency-legal-document-review

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

• Third-party content exposure detected (high risk: 0.70). The skill’s workflow is designed to analyze the user-provided “document” content (contracts/leases/litigation filings) for attorney-ready summaries and clause-by-clause flags; if that document text is sourced from an outsider (e.g., a third-party’s contract, issue/PR text, or a downloaded/forwarded attachment), that outsider-authored free text would be ingested into the agent’s LLM context during the substantive review steps.