ml-paper-writing

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

• Third-party content exposure detected (high risk: 0.90). The skill's mandatory citation workflow and code (see "Citation Workflow" / references/citation-workflow.md and the SKILL.md sections recommending Exa MCP and showing Python code) instruct the agent to query and ingest open/public third-party sources (Semantic Scholar, CrossRef/doi.org, arXiv, Exa MCP) and to programmatically read and validate their content as part of its workflow, which could allow untrusted, user-generated web content to influence subsequent actions.