perplexity

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

• Third-party content exposure detected (high risk: 0.90). The skill calls the Perplexity web-grounded API (https://api.perplexity.ai/chat/completions) to perform web searches and returns content and citations from public websites, which the agent ingests and displays—exposing it to untrusted, third‑party (potentially user-generated) content.