ClawHub
Back to skill

Security audit

social-listening-monitor

Security checks across malware telemetry and agentic risk

Overview

This skill openly runs a scoped social-search script using a SocialListeningAPI key to retrieve public posts, without persistence or hidden data handling.

Before installing, confirm you are comfortable letting the agent spend SocialListeningAPI credits and send chosen search queries to that provider. Results are public-search leads and should be reviewed before making business decisions.

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
87% confidence
Finding
The skill instructs the agent to execute a local Node.js script and to pass sensitive/runtime values through environment variables, while the skill declares no corresponding permissions. That mismatch is dangerous because it hides the skill's effective capabilities from reviewers and policy enforcement, and the script also depends on an inherited API key plus outbound access to external platforms via SocialListeningAPI.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/search-social.js:81