Back to skill

Security audit

Polymarket Aionmarket Trader

Security checks for vulnerabilities and agentic risk

Overview

This skill is openly for live Polymarket trading, but it asks agents to handle wallet private keys and reusable trading credentials in ways that could expose funds or accounts.

Review before installing. Use this only if you understand that it can support live financial trading. Prefer pre-signed orders or an external wallet/signer, do not paste a wallet private key into chat, avoid storing private keys in environment variables, confirm the exact Aionmarket endpoint before sharing credentials, and require a final review of market, side, size, price, wallet, and live environment before any order is submitted.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (3)

T09 · Insecure Skill Coding Practices

Error
Location
references/aionmarket-polymarket.md:5
Finding

Reusable Polymarket Credentials Are Transmitted to a Third-Party Service

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
clawhub.json:39
Finding

Configurable Base URL Can Redirect Authentication Secrets to an Attacker-Controlled Host

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
assets/trade-request-template.md:5
Finding

Workflow Solicits Raw Wallet Private Keys Through Chat or Environment Variables

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The template explicitly asks the user to provide extremely sensitive secrets, including an Aionmarket API key, Polymarket API secret/passphrase, and especially a wallet private key, directly in conversational workflow text. Collecting these values in plain skill prompts creates a high risk of credential exposure through logs, prompt history, analytics, or unintended model handling, and the trading context increases severity because compromise could directly enable unauthorized trades or theft of funds.

Content

No source excerpt is available for this finding.

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The document recommends falling back to a live trade submission endpoint for order execution but provides no warning that this can trigger real, irreversible financial transactions. Because this skill is specifically designed to place Polymarket trades, the lack of execution-safety guidance materially increases the chance of accidental or unauthorized order placement, especially if an agent proceeds without clear confirmation, environment checks, or transaction review.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill enables live trading, wallet credential registration, and order submission, all of which are state-changing and can cause direct financial loss or irreversible account effects. While the procedure mentions confirming simulation versus live trading, it does not require an explicit user-facing risk warning or a strong confirmation gate immediately before performing these sensitive actions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This reference material instructs the agent to collect and submit highly sensitive Polymarket API credentials without any warning about secrecy, storage minimization, redaction, or safe handling. In the context of an agent skill that explicitly accepts wallet credentials and private trading material, omission of these safeguards increases the risk of credential exposure through logs, prompts, transcripts, or unsafe persistence, which could enable unauthorized trading or account takeover.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.