ClawHub
Back to skill

Security audit

Package Version Tracker

Security checks across malware telemetry and agentic risk

Overview

This is a simple npm/PyPI version lookup skill with minor trigger-word ambiguity but no evidence of hidden, destructive, or credential-seeking behavior.

Reasonable to install for public npm and PyPI version checks. Be aware that queried package names are sent to public registries and that broad triggers like "pip show" or "package version" may activate the skill unintentionally; prefer explicit /version commands when using it.

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 (3)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger phrase "package version" is broad enough to match ordinary user conversation about software versions, which can cause unintended skill invocation. In an agent environment, ambiguous activation can route unrelated prompts into this skill, creating confusion, data leakage through unexpected external lookups, or unsafe chaining with other tools.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger phrase "pip show" overlaps directly with a common shell command, so users may mention it descriptively or in code examples without intending to invoke this skill. That ambiguity is risky because an agent may misinterpret command discussion as a request to perform network lookups or other actions.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger phrase "package version" is generic and could match ordinary user requests that are not specifically intended to invoke this skill. Because the skill has network permission and handles broad package-lookup functionality, accidental invocation could cause unintended routing of user queries and unnecessary external requests, though the direct security impact from this metadata alone is limited.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.