ClawHub
Back to skill

Security audit

Watchboard Intelligence

Security checks across malware telemetry and agentic risk

Overview

This skill transparently queries Watchboard’s public API and temporarily caches public responses, with no credentials or unrelated system access requested.

Install only if you are comfortable with the agent contacting watchboard.dev and storing temporary public API/RSS responses in /tmp/watchboard-cache. Treat returned intelligence data as external content and verify high-stakes claims with primary sources.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill describes capabilities that perform outbound network access to a public API and local file writes for caching, yet no explicit permissions are declared. This creates a trust and policy gap: reviewers and runtime controls may not realize the skill can contact external services and write to disk, which can enable unintended data exposure, persistence, or policy bypass if the surrounding platform relies on declared permissions.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal