ClawHub
Back to skill

Security audit

Geo Fact Checker

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent fact-checking assistant that uses disclosed web research and a local helper script, with no hidden credential access, persistence, or destructive behavior found.

Install this if you want structured fact-checking for drafts, comparisons, and data-heavy content. Be aware it may encourage web verification for a wide range of factual content, so avoid using it on confidential drafts unless external lookup of related facts is acceptable.

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 (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill explicitly says to use it aggressively and to prefer triggering it whenever there is any non-trivial factual content that might affect trust. That broad activation guidance can cause the agent to invoke this skill for many ordinary content tasks, increasing unnecessary web/tool use, expanding exposure of user content to external sources, and creating opportunities for prompt-scope drift or unintended data handling.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The manifest description uses expansive wording such as applying the skill whenever users want to increase trust, validate sources, or work on data-driven articles. Because manifest text is often used for routing, this can over-match broad writing and research scenarios, leading to unintended activation and unnecessary external verification behavior.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.