acquia
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). Yes — SKILL.md's "Proxy requests" section explicitly instructs using "membrane request CONNECTION_ID /path/to/endpoint" to fetch arbitrary Acquia API/site content (third-party, user-managed web data) that the agent is expected to read and could materially influence subsequent actions.
Audit Metadata