web3-dev

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to call and parse live responses from the public Blockscout PRO API (e.g., https://api.blockscout.com and endpoints such as GET /api/json/config and /{chain_id}/api/v2/...), ingesting public, user-generated blockchain/explorer data and using those responses to drive endpoint selection, pagination, polling, and subsequent actions—i.e., untrusted third‑party content is read and materially influences behavior.