unblu

Warn

Audited by Snyk on Apr 2, 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's SKILL.md instructs the agent to use Membrane to call Unblu APIs (see "Proxy requests" / membrane request CONNECTION_ID /path/to/endpoint) and to run/discover actions that operate on Conversation/Message/Visitor data, which can return untrusted, user-generated messages from third-party visitors that the agent would read and could influence subsequent actions.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 2, 2026, 07:55 AM
Issues
1