perplexity-researcher-reasoning-pro

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

• Third-party content exposure detected (high risk: 0.90). The skill's Research Methodology (Phase 2 & Phase 4) explicitly instructs the agent to run broad/targeted web searches and to fetch and evaluate public websites, GitHub repos, Stack Overflow, blogs and forum content (e.g., "Round 1/2/3: ... proceed to fetch", "Priority 2: Stack Overflow", and the gh/git commands), meaning it ingests untrusted third-party content that could carry indirect prompt injection.