cli-anything-exa

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly uses the Exa web search API and the "search" and "contents " commands to fetch full-text or highlighted content from arbitrary public web pages/URLs, which the agent is expected to read and synthesize into decisions—exposing it to untrusted third-party content that could carry indirect prompt injections.