sim

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

• Third-party content exposure detected (high risk: 0.70). The skill's required workflows (SKILL.md and reference docs like references/evm-collectibles.md and references/evm-tokens.md) direct the agent to run dune sim commands that fetch public on-chain data and user-supplied token/NFT metadata (including image_url/IPFS URIs and descriptions) from open/public sources, and the agent is expected to parse and act on those JSON responses as part of its decision-making, which could allow untrusted, user-generated content to influence behavior.