kairos

Warn

Audited by Snyk on Mar 16, 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 instructs the agent to call the Kairos Neo API which “searches across multiple platforms” (Taobao, Ele.me, Meituan, etc.) and returns product listings, click/tracking URLs and other third‑party content that the agent must read, format, display, and act on (see "Multi-Source Routing", the POST /ads/neo API and "Presenting Results" sections), so untrusted external content can materially influence agent behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 16, 2026, 03:06 PM
Issues
1