postmark
Warn
Audited by Snyk on Mar 29, 2026
Risk Level: MEDIUM
Full Analysis
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 using Membrane to run Postmark actions like "search-outbound-messages", "get-outbound-message-details" and proxy arbitrary requests to the Postmark API, which ingest user-generated email/message content from a third-party service that the agent would read and could materially influence subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata