string-database

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

• Third-party content exposure detected (high risk: 0.80). The skill directly fetches and returns data from the public STRING REST API (https://string-db.org/api) via functions like string_network, string_enrichment and string_interaction_partners, so the agent ingests and parses open/public third-party content (TSV/JSON/PNG) that could contain untrusted user- or literature‑derived text and thus enable indirect prompt injection.