ClawHub

Package Updater

Security checks across malware telemetry and agentic risk

Overview

This is a simple dependency-maintenance instruction skill; it can lead to package changes, but that behavior matches its stated purpose and is not hidden.

Install only if you want an agent to help maintain dependencies. Use a read-only outdated report first, review changelogs and diffs, approve each patch/minor/major update explicitly, and run it only in repositories where you trust package-manager scripts.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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 (2)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger phrases are broad enough to match common maintenance requests, which increases the chance the skill activates in situations where the user did not explicitly consent to dependency-changing workflows. Because this skill can lead to package update commands and project modifications, overbroad activation expands the attack surface for unintended or unsafe changes.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill describes checking and updating dependencies but does not prominently warn that these actions can modify manifests, lockfiles, and transitive dependency trees or introduce breaking changes. In practice, users may invoke the skill expecting a read-only audit, while the described workflow includes update behavior that can affect builds, tests, and production behavior.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal