pipes-abi

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to fetch and parse ABIs and research data from public third‑party sites (e.g., WebFetch calls to Etherscan/Basescan in "Step 2: Fetch ABI" and WebFetch calls to Addybook.xyz in references/RESEARCH_CHECKLIST.md), which the agent will read and interpret as part of its workflow and can change subsequent actions (fetch implementation ABIs, generate types, pass schemas), so it exposes the agent to untrusted third‑party content.