nanoresearch-ideation

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to search arXiv and Semantic Scholar (via the required tools search_arxiv and search_semantic_scholar) and to analyze the retrieved public papers as part of its workflow, which exposes it to untrusted third-party content that can influence decisions.