alterlab-string-db

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 ingests data from the public STRING API (https://string-db.org/api) via scripts/string_api.py and the SKILL.md workflows show the agent parsing and acting on returned TSV/JSON (e.g., string_enrichment, string_network, string_interaction_partners) so untrusted third-party content can materially influence subsequent analysis and tool use.