ClawHub
Back to skill

Security audit

Ripgrep

Security checks across malware telemetry and agentic risk

Overview

This is a normal ripgrep reference skill with standard install metadata and no hidden execution or persistence.

Install this if you want ripgrep command help. Be careful with examples that search hidden or ignored files, and preview matches before running bulk replacement commands such as `xargs sed -i`, especially outside version-controlled directories.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill includes a command pipeline that performs in-place edits via `sed -i` after enumerating files with `rg -l`, but it does not explicitly warn that this modifies files on disk. In an agent-skill context, users may copy or automate examples directly, so omission of a warning increases the risk of unintended bulk changes or corruption across many files.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.