interview

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 fetches third-party content: Step 0's version check runs a curl against https://api.github.com/repos/.../releases/latest and Path 4 directs using WebFetch/WebSearch to gather external web information, so the agent will read and act on untrusted public web content as part of its workflow.