block-inventory

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly instructs the agent to run public searches (e.g., .claude/skills/.../search-block-collection-github.js) and visit live example URLs such as https://main--aem-block-collection--adobe.aem.live/block-collection/{block-name} to read and infer block purposes, meaning it fetches and interprets untrusted public web content that can influence subsequent decisions.