ClawHub
Back to skill

Security audit

Polyvision

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a disclosed Polymarket analytics integration that uses an API key and only changes saved watchlist or API-key state when explicitly requested.

Install only if you are comfortable giving PolyVision its own API key and sending wallet-analysis requests to its hosted service. Treat output as financial research, not investment advice, and only authorize portfolio changes or API-key regeneration/deactivation when you explicitly intend those account changes.

SkillSpector

By NVIDIA
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 (1)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The documented auth response includes sensitive account metadata, including full email address and an API key prefix. While not a full secret, exposing account identifiers and key metadata increases account fingerprinting risk and can aid phishing, user enumeration, and operational reconnaissance if surfaced unnecessarily to end users or logs. In a trading/analytics skill context, auth metadata is not essential to most user workflows, so its inclusion is harder to justify and more dangerous.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:63