customer-pulse

Warn

Audited by Snyk on May 13, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill's Workflow (steps 2–6 in SKILL.md) explicitly fetches PayPal disputes, HubSpot tickets, Gmail threads, Intercom conversations and accepts pasted Google/Yelp reviews — all untrusted/user-generated third‑party content — and requires extracting verbatim quotes and deriving themes and action items from them, so that external content directly influences the agent's decisions and outputs.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 13, 2026, 05:32 PM
Issues
1