string-database

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

• Third-party content exposure detected (high risk: 0.85). At runtime the skill calls STRING’s public REST API endpoints (e.g., /api/tsv/enrichment, /api/tsv/network, /api/tsv/interaction_partners) and ingests the returned TSV/JSON text (including description/term fields) into the agent context, which is outsider-authored free text from an external public database.