euler-irm-oracles

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

• Third-party content exposure detected (high risk: 0.70). The skill includes TypeScript examples that fetch and parse live Pyth Hermes API data from https://hermes.pyth.network/api/latest_vaas (rules/oracle-deploy.md and AGENTS.md) and then uses those external VAAs as updateData for on-chain operations, so the agent clearly ingests untrusted third-party content as part of its workflow.