groq-inference

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly uses the compound-beta model with built-in web_search and visit_website tools that fetch and return public webpage content (see SKILL.md, reference/tool-use-patterns.md, and templates/groq-client.py), so untrusted third-party pages can be ingested and materially influence the agent's subsequent actions.