pitch-deck-reviewer

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and read third‑party web content (e.g., "Google Slides links — Use WebFetch to access shared slide content if publicly available" and "If you need to look something up, use WebSearch" in SKILL.md), so the agent will ingest untrusted public/user-generated content and use it to drive analysis and decisions.