Back to skill

Security audit

Polymarket Nothing Ever Happens

Security checks for vulnerabilities and agentic risk

Overview

This trading skill is not clearly malicious, but it needs Review because it can use financial credentials and performs an account-changing redemption step even in modes described as scan-only or dry-run.

Treat this as a high-impact financial automation skill. Do not install it with a production wallet key or meaningful funds unless the redemption behavior, dependency pinning, and default-setting mismatch are fixed. Use paper trading or a dedicated low-balance wallet, avoid scheduled live runs, and verify the exact SDK and gamma_api.py source before enabling live trading.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (4)

T09 · Insecure Skill Coding Practices

Error
Location
nothing_ever_happens.py:537
Finding

Account redemption is invoked in scan and dry-run modes

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
SKILL.md:45
Finding

Security-sensitive Simmer SDK dependency is not version-pinned

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
nothing_ever_happens.py:209
Finding

Mutable sibling module is inserted into the Python import path and executed

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
nothing_ever_happens.py:44
Finding

Executable trading defaults materially exceed the documented strategy defaults

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill instructs users to provide a live wallet private key for trading, but the warning is operational rather than security-focused and does not prominently explain the risks of storing, exposing, or reusing a private key. Because a private key grants full control of funds, weak guidance here can lead to credential compromise and irreversible asset theft.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding

The skill requests and uses sensitive environment-based secrets (SIMMER_API_KEY and especially WALLET_PRIVATE_KEY) but does not declare any explicit tool scope or permissions boundary. In an agent ecosystem, missing capability declarations reduce transparency and can allow users or orchestrators to install a skill without understanding that it needs secret material and can perform live trading actions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The quick-start commands include --live execution, but the documentation does not prominently warn that this will place irreversible real-money trades using the configured wallet and available funds. In a trading skill, understated live-trading warnings increase the chance of accidental financial loss from user misunderstanding, automation mistakes, or unsafe defaults.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest solicits a WALLET_PRIVATE_KEY for self-custody trading but does not present an explicit warning that this is a highly sensitive secret that grants signing authority over funds. In a trading skill, users may paste a production private key without understanding the risk surface, increasing the chance of credential theft, accidental disclosure, or unsafe handling by downstream components.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest describes a skill that scans markets, filters candidates, checks fees, and executes NO purchases. However, the code also calls auto_redeem() to redeem winning positions before scanning, which is a separate portfolio-management action not mentioned in the stated behavior.

Content

No source excerpt is available for this finding.