stock-research-engine

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of Markdown instructions and JSON metadata. No executable scripts (.py, .js, .sh), binaries, or configuration files for package managers were found.
  • [EXTERNAL_DOWNLOADS]: The instructions reference well-known financial data providers including Yahoo Finance, Financial Modeling Prep (FMP), East Money (东方财富), and Xueqiu (雪球). These are legitimate, standard sources for the skill's stated purpose of financial analysis.
  • [PROMPT_INJECTION]: The skill adopts a professional persona ("buy-side fund manager"). This is a task-specific behavioral instruction and does not attempt to bypass safety guardrails, override system instructions, or extract internal system prompts.
  • [DATA_EXFILTRATION]: No patterns related to sensitive file access, credential harvesting, or unauthorized network operations were detected. The skill's focus is on retrieving public financial data for user-requested stock analysis.
  • [SAFE]: The skill contains no obfuscation, hidden URLs, or encoded content. All instructions and metadata are provided in plain text.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 01:02 AM
Security Audit — agent-trust-hub — stock-research-engine