idea-discovery-robot

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

• Third-party content exposure detected (high risk: 0.90). The skill's Phase 1 ("Robotics Literature Survey") explicitly invokes /research-lit and directs searching recent papers from public venues and arXiv (see "Search Priorities" and the /research-lit invocation), and those harvested third‑party findings are then used to drive idea generation, filtering, novelty checks, and reviewer decisions, so untrusted public content can materially influence the agent's actions.