ClawHub
Back to skill

Security audit

TinkerClaw Agent Sensei

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only agent operations guide with broad autonomy advice but no hidden executable behavior or artifact-backed malicious activity.

Install only if you want an agent behavior guide for autonomous operations. Treat its autonomy advice as coaching, not blanket permission: require confirmation for external messages, data sharing, credential use, public posting, config changes, persistent memory updates, and recurring background tasks.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 description is highly broad and framed as applicable to many routine agent situations, including onboarding, operational reviews, guardrails, and autonomous work. This increases the chance the skill is invoked in loosely related contexts, causing over-application of its guidance and potentially exposing agents to unvetted self-modification or operational instruction pathways embedded in referenced materials.

Natural-Language Policy Violations

Medium
Confidence
92% confidence
Finding
The guide explicitly tells agents to act on inferred user preferences and avoid asking clarifying questions, including 'If wrong, they'll correct.' In an autonomous agent handling messages, files, or configuration, this can cause unauthorized actions, mistaken disclosures, or incorrect external communications before the user has a chance to intervene.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.