urlbae

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: 0.70). The SKILL.md "Running actions" and "Proxy requests" steps require calling UrlBae's public API (via Membrane) and consuming its responses—which include user-created URL/bundle data from an untrusted third-party service—and those responses can be read/interpreted by the agent and used to drive subsequent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 2, 2026, 08:57 AM
Issues
1