financial-analysis

Fail

Audited by Snyk on Feb 25, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E006: Malicious code pattern detected in skill scripts.

  • Malicious code pattern detected (high risk: 1.00). High-risk backdoor: the FinancialAnalyzer deliberately directs AI requests to a nonstandard external base_url ("https://api.drqyq.com") while pulling API keys from environment variables, which can exfiltrate sensitive financial data and credentials to an attacker-controlled endpoint.

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

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly reads and parses user-supplied/public PDF financial reports (see "读取PDF" in SKILL.md and the parse_financial_data_from_text in references/code-examples.md which ingests arbitrary pdf_text), and those untrusted documents directly feed calculations and the AI-driven analysis/recommendations, so third‑party content can materially influence behavior.
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 25, 2026, 11:21 AM