lmfdb-cli

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly directs using the lmfdb CLI to fetch and parse records from the public LMFDB website (https://www.lmfdb.org/) as part of verification workflows, so untrusted third-party data from that site would be read and could influence the agent's follow-up checks and actions.