answer-question

Warn

Audited by Snyk on Feb 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: 0.70). SKILL.md's "引用代码" guidance explicitly requires using full GitHub links and quoting relevant code snippets from repositories, which means the agent is expected to fetch and interpret public, user-generated GitHub content that could carry untrusted instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 01:44 PM