magnolia
Warn
Audited by Snyk on Apr 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly instructs the agent to fetch and interact with Magnolia content via Membrane commands such as "membrane action run --connectionId=... ACTION_ID" and "membrane request CONNECTION_ID /path/to/endpoint", which will ingest CMS pages/assets and API responses (potentially user-generated/untrusted) that the agent is expected to read and could materially influence subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata