Back to skill

Security audit

Polymarket Trader 1.0.0

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed market-analysis helper that fetches public Binance data and optionally reads local fill logs, without trading, persistence, or credential use.

Install only if you are comfortable with a trading-analysis skill that uses live Binance market-data requests and may read local paperbot fill logs. It does not place trades or use credentials, but financial strategy outputs should be independently checked before acting on them.

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
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (6)

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
The CLI help text is presented in Korean, which imposes a specific language on users without offering a choice. The file also includes additional Korean user-facing output elsewhere, indicating a locale-specific UX that is not documented as region-specific or optional.

Natural-Language Policy Violations

Medium
Confidence
92% confidence
Finding
The script prints operational notices such as missing-file and no-data messages in Korean only. For a general-purpose script, this is a language-policy issue unless the Korean-only constraint is explicitly documented and justified.

Natural-Language Policy Violations

Medium
Confidence
90% confidence
Finding
The main results banner includes Korean text and does not provide any locale selection. This forces a specific language in normal operation without user consent or documentation that the tool is region-specific.

Natural-Language Policy Violations

Low
Confidence
95% confidence
Finding
The argument help string is written only in Korean ("분석할 심볼"), which imposes a specific language in user-facing text without offering an alternative or opt-in. This matches the language/locale policy concern for natural-language content embedded in code.

Natural-Language Policy Violations

Low
Confidence
90% confidence
Finding
The command-line help string is written only in Korean ("분석할 심볼 (예: ETHUSDT)"), which imposes a specific language on users without any opt-in or alternative. The policy specifically calls for flagging language or locale constraints when the skill does not offer a language choice or clearly justify the restriction.

Missing User Warnings

Low
Confidence
82% confidence
Finding
The script performs HTTP requests in `fetch_json`, which is then used to query Binance market endpoints. While this is not inherently dangerous, there is no docstring, comment, or user-facing notice near the network operation explaining that the script will contact an external service.

Static analysis

No suspicious patterns detected.