ClawHub
Back to skill

Security audit

Social Media Analytics

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed read-only connector for social media analytics, with the main risk being that its connector URL acts like a password.

Install only if you trust Boring with analytics and account metadata for the connected social accounts. Treat the MCP connector URL like a password, avoid sharing it, confirm the connected permissions are read-only, and revoke or regenerate the token when you stop using it or if it is exposed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The skill description uses broad trigger phrases like 'show my analytics', 'view stats', and 'how are my posts doing', which are common conversational requests and may cause the skill to activate in contexts the user did not explicitly intend. Because this skill connects to a third-party analytics service using an embedded MCP credential, unintended invocation could expose account metadata or performance data more readily than necessary.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.