research-collaborator

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (SKILL.md rule 3: "Search 3+ query variations for prior work" and the Delivering Results template "Prior work: [what you found, with links]") explicitly requires performing web/literature searches and ingesting public third-party content (links, papers, issues), which the agent must read and use to drive novelty assessment and experimental recommendations — enabling indirect prompt injection from untrusted sources.