quick-topic-researcher

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly performs parallel searches against public web sources — e.g., Perplexity ("Perplexity" in Research Sources and perplexity_ask in the Technical Implementation / scripts) and a generic WebSearch tool plus direct URL fetches to guideline sites — and the agent is instructed to consume and synthesize those third‑party/web search results as part of its workflow, which exposes it to untrusted open-web content that could carry indirect prompt injection.