ds-baseline

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly instructs the agent to "use web search for discovering papers or repos" and to read source ArXiv papers via artifact.arxiv(...) as part of the required analysis workflow (SKILL.md non-negotiable rules), which clearly ingests open/public third‑party content that can influence decisions and tool use.