mql5-pro
Fail
Audited by Snyk on Aug 25, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (high risk: 1.00). The skill contains a "self-correction protocol" that explicitly orders the agent to edit and update the skill files immediately (in-turn), which is an instruction to modify the agent's own system/skill content and thus is a hidden/deceptive directive outside the skill's stated purpose of producing MQL5 code.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). Skill runtime path reads MT5 “Experts/Journal logs” files (via the bundled MT5 log autonomous reading workflow in
references/pitfalls.md§10), which can contain free-textPrint/PrintFormatoutput authored by the user/attacker’s EA code or other first-party but user-authored sources.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 1.00). The skill is explicitly about writing MetaTrader 5 trading programs and includes concrete trade-execution APIs and tooling: it names CTrade/MqlTradeRequest/OrderSend, ships trade-execution headers in assets/Trade, provides an EA template and sample code that instantiate CTrade and perform trading logic, and even lists a terminal bridge (mcp-metatrader5-server) capable of demo-account trade execution. These are specific, not generic, capabilities to place/manage market orders and thus constitute Direct Financial Execution authority.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (high risk: 0.90). The skill explicitly instructs the agent to immediately modify the skill files in-place (searching and editing SKILL.md and every references/* and assets/*), which directs the agent to change local files/state and thus can compromise the machine's state.
Issues (4)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata