tushare

Fail

Audited by Snyk on Nov 21, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill is a documented Tushare data reference, but every code example routes calls through an undocumented internal wrapper, src.data_gateway.skill_sources.tushare_client, that receives the user's live TUSHARE_TOKEN, and the skill never explains what that wrapper does with it, so this is sketchy but not shown to be malicious.

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

  • Third-party content exposure detected (low risk: 0.10). The required quickstart (install tushare, set token, call pro.stock_basic) returns structured Tushare API data, but the catalog includes on-demand endpoints such as 深证/上证易互动问答 (investor Q&A) and 新闻快讯, which return outsider-authored text only when the agent selects and queries them.

Issues (2)

E004
CRITICAL

Prompt injection detected in skill instructions.

W011
MEDIUM

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

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 21, 2026, 05:37 PM
Issues
2