ClawHub

Exec Reducer

Security checks across malware telemetry and agentic risk

Overview

This skill is a simple file helper, but it can read, search, list, and overwrite arbitrary local files without clear limits or safeguards.

Install only if you are comfortable giving the agent a generic local file helper. Use it in a constrained workspace, check paths explicitly before read/search/write commands, and avoid using it on sensitive directories or important files unless you have backups.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger condition 'when needing batch file processing, searching, or writing' is very broad and can cause the skill to be invoked in many situations involving sensitive files or destructive actions. Because the skill wraps execution of read/write/search operations without documented guardrails, ambiguous triggering increases the chance of unintended file access or modification.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The documentation explicitly exposes a write capability but does not warn that it can modify or overwrite user data, which creates a meaningful safety and integrity risk. In an agent setting, undocumented write behavior can lead to accidental destructive changes, especially when combined with broad invocation criteria.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The script performs arbitrary file writes directly from command-line input with no path restrictions, confirmation, or safety checks. In an agent skill context, this increases the risk of accidental or unauthorized overwriting of files, including prompts, configs, or other sensitive workspace artifacts, especially if upstream inputs are attacker-influenced.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal