ai-agent-papers-guide

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md "Tracking New Papers" section includes a Python arxiv search snippet that fetches and ingests public arXiv results (open third-party content) which the agent is expected to read and use to update its paper list, allowing external content to influence its workflow and decisions.