postmark

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

• Third-party content exposure detected (medium risk: 0.30). The Postmark skill manages transactional emails, bounces, and inbound rules, allowing the agent to ingest external email messages and bounce details containing outsider-authored free text.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill executes npx @useclawlink/cli referencing an unverified third-party package publisher from an external registry, representing an unverifiable runtime external dependency under a weak tier.