perplexity-advanced-troubleshooting

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow ingests outsider-authored free text when it sends user-provided “query”/messages content to Perplexity’s https://api.perplexity.ai/chat/completions endpoint (Layer 4/quality check and the citation/latency/recency test functions), which can include arbitrary external instructions.