sinch-fax-api

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to accept and fetch arbitrary external documents via contentUrl and to process inbound webhook callbacks (attachments, filenames, metadata) under "Common Patterns" and "Security — untrusted content", so untrusted third-party content is fetched and can influence agent actions.