epc-search

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

• Third-party content exposure detected (low risk: 0.10). The skill’s runtime workflow performs searches via the MCP tools search_patent_law / search_mpep, which implies the LLM ingests retrieved external legal text in response to a user-supplied query but the provided skill spec does not show an explicit, attacker-controlled “outsider authored” text submission path being read without active searching.