ClawHub
Back to skill

Security audit

AI Agent Governance

Security checks across malware telemetry and agentic risk

Overview

The skill appears to use external policy-evaluation APIs for its stated purpose, with a privacy caution but no evidence of hidden or malicious behavior.

Install only if you are comfortable sending the evaluation request details to the operator's external API. Avoid including secrets, private customer data, or unnecessary infrastructure details in action payloads unless you have reviewed the provider's privacy and retention terms.

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
95% confidence
Finding
The skill explicitly instructs users to send agent identity, policy-evaluation context, and action payloads to live third-party APIs, but it does not clearly warn about the resulting data transmission, retention, or privacy implications. In practice, `actionPayload` may include sensitive operational, personal, or infrastructure data, so users could disclose confidential information to an external service without informed consent or minimization.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.