RedHat File Operations

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed file-operations helper with safety checks, but its activation metadata is malformed and should be fixed before relying on automatic triggering.

Install this only in agents that are constrained to the intended workspace, and require explicit approval for delete, overwrite, recursive, or bulk operations. The publisher should replace the malformed trigger metadata with clear trigger phrases and scope limits.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The manifest declares a triggers section, but the value shown is just `System.Object[]`, which does not communicate what phrases, conditions, or scope activate the skill. This is overly vague for a manifest file because users and routing systems cannot tell when the skill should or should not be invoked.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal