acf
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 "Proxy requests" section explicitly lets the agent send arbitrary requests via Membrane to an ACF/WordPress API and receive untrusted, user-generated content (posts/fields) which the agent is expected to read and could materially influence subsequent actions.
Audit Metadata