ClawHub
Back to skill

Security audit

Model Pilot

Security checks across malware telemetry and agentic risk

Overview

This skill only gives model-choice and cost-saving advice, with disclosed live pricing lookups and no executable code or credential access.

Expect this skill to occasionally suggest cheaper models and to use live web lookups for current pricing. Review any separate 'install full suite' command carefully because it installs additional skills beyond this one.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Low
Confidence
95% confidence
Finding
The language policy says to detect the user's message language but then sets a default of English. Per the policy, forcing a specific language or locale without user opt-in can be a natural-language policy violation unless the user is explicitly offered a choice or the constraint is justified.

Credential Access

High
Category
Privilege Escalation
Content
- Does NOT switch models automatically — recommends only
- Does NOT persist anything
- Does NOT access credentials
- Does NOT modify any files

## More by TommoT2
Confidence
70% confidence
Finding
access credentials

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal