perplexity

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md shows it calls Perplexity's Sonar API (e.g., POST to https://api.perplexity.ai/chat/completions) which performs real-time web search and returns synthesized answers/citations used directly in workflows such as "Research Paper Summary" and "Real-Time News Monitoring", so the agent ingests and acts on untrusted public web content.