forex-edge

Fail

Audited by Snyk on Mar 27, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The prompt asks the user for MT5 credentials (server/login/password) and instructs running commands that embed the password as a CLI argument (e.g., --password {PASSWORD}) and saving it in config.json, which forces the agent to handle and output secrets verbatim — high exfiltration risk.

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

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs cloning a public GitHub repo (git clone https://github.com/Hero988/Forex-Trading-Skill.git) and then running scripts from that repo (e.g., scripts/*.py like run_full_backtest.py, generate_ea.py), so the agent fetches and executes public third‑party content which can materially influence decisions and tool use.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 1.00). The skill clones and later runs scripts from the external repository at runtime (git clone https://github.com/Hero988/Forex-Trading-Skill.git .), so fetched remote code would be executed locally and thus directly controls the agent's behavior.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

  • Direct money access detected (high risk: 1.00). The skill is explicitly built to produce and deploy MetaTrader 5 Expert Advisors that autonomously open, size, manage, and close live trades. It requests MT5 server/login/password, provides mt5_connect.py and scripts to pull historical data, generate .mq5 EA files, compile/install them, and contains EA features like risk-based position sizing, market entry/exit logic, emergency close, kill switch, and trade management (T1/T2, trailing stops, float cap). The prompt even states the generated EAs "trade on MetaTrader 5 without human intervention." These are direct market-order execution capabilities, so this is direct financial execution authority.

Issues (4)

W007
HIGH

Insecure credential handling detected in skill instructions.

W011
MEDIUM

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

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

W009
MEDIUM

Direct money access capability detected (payment gateways, crypto, banking).

Audit Metadata
Risk Level
HIGH
Analyzed
Mar 27, 2026, 02:00 PM
Issues
4