add-vault-protocol

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and parse contract ABIs and implementation data from public blockchain explorers (e.g., Etherscan/Arbiscan/Basescan) and to search/consume protocol homepages, GitHub, and other web resources for docs and metadata, so it ingests untrusted third-party content that the agent will read and interpret.