cloudmersive

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly lists actions like "Scan Website for Threats", "Validate URL", and "Convert HTML to PDF" that operate on arbitrary public website URLs or HTML content, meaning the agent will fetch and process untrusted third‑party web content as part of its workflow.