ClawHub
Back to skill

Security audit

identify-rd-directions-rd

Security checks across malware telemetry and agentic risk

Overview

The skill is a disclosed R&D report workflow whose file creation and optional evidence searches fit its stated purpose.

Install only if you want a workflow that can create report files and, when you authorize research, query patent, literature, standards, or web sources. Use confidentiality-minimized wording for sensitive projects and choose an explicit output directory.

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
94% confidence
Finding
The skill explicitly instructs the agent to read local files, write artifacts, invoke a renderer script, and perform external network queries, yet no declared permissions are present. This creates a capability/permission mismatch that can bypass governance controls, causing the skill to appear less powerful than it actually is and increasing the risk of unintended file modification or data exfiltration in a high-privilege runtime.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.