c-email
Warn
Audited by Snyk on Mar 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md shows the agent will read and act on external email via gog/himalaya (e.g., "gog mail read", "himalaya read" and send/reply commands), which exposes it to untrusted, user-generated email content that could contain instructions influencing subsequent actions.
Audit Metadata