blockchain-intelligence-playbook

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md index explicitly instructs or routes to skills that open and read public web resources (e.g., "armaniferrante-x-status-solana-reference" — "open URL for verbatim text", "phalcon-compliance-documentation" — "read live site for features", and "katana-web-crawling"), which means the agent will fetch and interpret untrusted public/user-generated content as part of its workflow and could let that content influence decisions.