polymarket-telegram-picks

• Outcome: Pass
• Latest audit: May 29, 2026, 8:17 PM
• Version:
  1.0.0

Overview

This skill is a disclosed Polymarket NBA odds-to-Telegram notifier, with no evidence of hidden data access or malicious behavior.

Install only if you want OpenClaw to fetch Polymarket NBA data and send AI-generated betting recommendations to your configured Telegram chat. Protect the bot token, confirm the chat ID, review any cron schedule before enabling it, and treat the recommendations as risky gambling-related content rather than financial advice.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (4)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 94% confidence
• Finding: The skill instructs the agent to execute local scripts, access environment variables or config files for Telegram credentials, and perform network exfiltration to Telegram, yet it declares no permissions. This weakens user awareness and platform enforcement, making it easier for a user to invoke a skill that can read secrets and send data externally without an explicit trust boundary.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 97% confidence
• Finding: The documented behavior materially differs from the actual capability set: the skill can read local Telegram credentials, send messages externally, and may only fetch NBA summaries rather than perform the broader AI recommendation workflow claimed. Description-behavior mismatch is dangerous because users may authorize the skill under false assumptions, while hidden data access or outbound transmission occurs outside the expected scope.

Vague Triggers

Medium

• Confidence: 84% confidence
• Finding: The trigger phrases are broad enough that normal conversation about Polymarket analysis or daily picks could activate the skill unintentionally. Because activation leads to shell execution and potential Telegram delivery, ambiguous triggering increases the chance of unintended external actions and data transmission.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The skill tells the agent to send analysis content to Telegram without an explicit warning or confirmation before external transmission. Any automatic outbound send can leak user-generated or model-generated content to a third-party service or wrong chat if credentials are misconfigured, making the lack of warning a meaningful safety issue.

VirusTotal

64/64 vendors flagged this skill as clean.