Security audit

Polymarket via Gina

Security checks for vulnerabilities and agentic risk

Overview

This skill is coherent but needs careful review because it enables authenticated real-money Polymarket trading and scheduled automations with limited detail on confirmations, limits, and reversibility.

Install only if you are comfortable giving this hosted MCP service authenticated access to your Polymarket-related wallet workflow. Before trading, verify that every order, redemption, cancellation, and automation requires an explicit confirmation you understand, set conservative limits, and know how to inspect, pause, or delete any scheduled Recipe.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The README encourages natural-language trading and automation actions such as placing bets, setting price conditions, and creating scheduled automations, but it does not present prominent warnings about financial loss, mistaken orders, automation risks, or the potential irreversibility of on-chain actions. In an agent-integrated context, users may treat prompts as low-friction commands and underestimate that they can trigger real money movement or persistent automated behavior, increasing the chance of harmful accidental actions.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The skill explicitly invites unrestricted natural-language commands for sensitive actions including trading, order cancellation, redeeming winnings, and setting up automations. In an agent ecosystem, vague activation boundaries can cause the skill to be invoked from loosely related user requests or chained prompts, leading to unintended real-money actions or dangerous overreach into authenticated financial capabilities.

Natural-Language Policy Violations

Low

Confidence: 81% confidence
Finding: The file states "Just type natural language prompts" and all examples are presented only in English, with no indication that other languages are supported or that English is merely illustrative. This can constitute a language-policy issue if the organization requires avoiding unnecessary language constraints without user opt-in.