trace-tx

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md workflow explicitly tells the agent to fetch and parse trace JSON from the public API "https://mevscan.matroos.xyz/api/tree/<tx_hash>", so the agent ingests and acts on untrusted third‑party content returned by that endpoint which can materially change its parsing, tree rendering, and summary behavior.