helpspace

Warn

Audited by Snyk on Mar 28, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.85). The skill's SKILL.md explicitly exposes and instructs the agent to fetch and read user-generated Helpspace content (tickets, ticket messages, articles) via Membrane actions and proxy requests (e.g., "List Ticket Messages", "Get Ticket", and the "membrane request" proxy), so untrusted third-party content could be ingested and influence subsequent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 28, 2026, 02:57 PM
Issues
1