perplexity-search

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly performs real-time web searches and ingests web‑grounded third‑party content via Perplexity/OpenRouter (see SKILL.md "Perplexity searches real-time web data" and scripts/perplexity_search.py which calls Perplexity models, plus references/model_comparison.md noting sonar-pro-search executes agentic multi‑step searches), so untrusted public content can be read and materially influence the agent's outputs and actions.