ClawHub
Back to skill

Security audit

Bom Checker

Security checks across malware telemetry and agentic risk

Overview

This skill only guides a BOM completeness review and report generation, with no hidden code, network use, credential handling, or destructive behavior found.

Install this if you want strict BOM completeness checks for visual inspection equipment. Review the generated reports carefully, especially if you do not read Chinese or if the BOM represents a device type that intentionally omits some listed components.

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
90% confidence
Finding
The manifest description includes broad trigger phrases like 'Use when checking BOM integrity' and 'preventing assembly line stoppages,' which can match ordinary user requests beyond a narrowly scoped BOM-audit task. This can cause unintended invocation, leading the agent to apply rigid BOM-checking behavior in contexts where the user did not explicitly request this skill.

Natural-Language Policy Violations

Medium
Confidence
78% confidence
Finding
The skill content is written entirely in Chinese and prescribes fixed Chinese report formats without offering any user-language negotiation. This can cause misunderstandings, incorrect user interpretation of warnings, or unusable output when the user operates in another language, especially in a high-consequence procurement or manufacturing workflow.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.