ClawHub
Back to skill

Security audit

rd-direction-finder

Security checks across malware telemetry and agentic risk

Overview

This skill performs disclosed research searches and creates local report files for its stated R&D-direction reporting purpose.

Install only if you want an agent to use external patent/paper/web search tools and create local Markdown, JSON, and HTML report files. Review or override the output path before running, and treat generated HTML as content derived from user input and search results.

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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill instructs the agent to read and write local files and build artifacts, but it does not declare permissions or clearly constrain where writes may occur. Undeclared filesystem capability increases the chance of unexpected local data exposure, overwriting artifacts, or abuse if the skill is invoked in a broader agent environment with ambient file access.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill directs automatic shell and Python execution plus local file generation in the same run, without an explicit user-facing warning or consent boundary. In agent environments, this can normalize silent command execution and filesystem writes, increasing the risk of unintended local changes, artifact clobbering, or unsafe chaining with attacker-influenced content.

VirusTotal

56/56 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.