freshdesk

Warn

Audited by Snyk on Apr 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: 0.80). The skill's SKILL.md explicitly instructs the agent to connect to Freshdesk and run actions like "list-tickets" and "get-ticket" (via membrane action run), which ingest user-generated ticket/contact content from the third-party Freshdesk system that the agent is expected to 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 28, 2026, 08:13 PM
Issues
1