xyq-skill

Warn

Audited by Snyk on Apr 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: 0.90). The skill's workflow (SKILL.md) and get_thread.py explicitly fetch messages from the third-party API (POST /api/biz/v1/skill/get_thread on https://xyq.jianying.com) and instruct the agent to read/interpret those messages (including intent-confirmation prompts and artifact URLs) and then take actions (reply, submit runs, download artifact URLs), so untrusted third-party content can materially influence tool use and decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 13, 2026, 09:24 AM
Issues
1