res-web

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md workflow explicitly instructs the agent to "Execute searches in parallel", evaluate and cross-reference web sources, and output findings with cited URLs (the "Sources" section), i.e., it fetches and interprets public third-party web content as part of its decision-making, exposing it to untrusted user-generated pages that could supply instructions.