pharmaclaw-ip-expansion-agent

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

• Third-party content exposure detected (high risk: 0.90). The agent explicitly fetches public patent and compound data (e.g., scripts/agent.py::fto_assess posts to the USPTO PatentsView API and GETs PubChem PUG REST as listed in references/apis.md), parses that third‑party content with NLP, and uses those results to drive FTO/infringement decisions and strategic recommendations, so untrusted external content can materially influence its actions.