Voice

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

• Third-party content exposure detected (high risk: 0.90). The skill's Multi-Channel Synthesis workflow (see references/multi-channel-synthesis.md Source Inventory and the SKILL.md Collect->Analyze steps) explicitly ingests public user-generated sources — e.g., App Store reviews, G2/Capterra (API or scraping), and social media — and requires the agent to normalize and act on that content, so untrusted third-party content can materially influence decisions and tool routing.