gosquared

Warn

Audited by Snyk on Apr 29, 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 the agent to run Membrane actions that fetch user-generated GoSquared data (e.g., "get-chat-messages", "get-chat", "list-people" in the "Popular actions" section), so the agent will ingest and interpret untrusted third‑party chat/CRM content from GoSquared which could contain instructions that affect subsequent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 29, 2026, 03:19 PM
Issues
1
Security Audit — snyk — gosquared