appcircle
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: 0.70). The SKILL.md explicitly instructs the agent to use Membrane to run actions and proxy arbitrary requests to the Appcircle API (see "Running actions" and "Proxy requests"), which causes the agent to fetch and interpret third‑party Appcircle API responses (potentially user‑generated/untrusted data) that can influence subsequent actions.
Audit Metadata