textline

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.md explicitly instructs using Membrane to query and proxy the Textline API to read Conversations/Messages and other customer-generated data (see "Textline Overview" and "Working with Textline" / proxy requests), so the agent will ingest untrusted third-party user content that could influence actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 2, 2026, 08:01 PM
Issues
1