mailgun
Warn
Audited by Snyk on Feb 19, 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 explicitly calls the Mailgun API (e.g., GET /mailgun/v3/{domain_name}/events, templates, messages.mime and related endpoints shown in SKILL.md) which returns user-generated/untrusted email content, events, and templates from external senders that the agent is expected to read/act on as part of its workflow, so third-party content could embed instructions that influence subsequent actions.
Audit Metadata