1msg
Warn
Audited by Snyk on Mar 4, 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 the agent to use Membrane to call 1msg APIs (e.g., the "Get Messages" action and the membrane request proxy) which fetches user-generated content from external 1msg endpoints that the agent would read and could drive subsequent actions.
Audit Metadata