ClawHub
Back to skill

Security audit

bom-toolkit

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent BOM spreadsheet toolkit that reads user-provided BOM files and writes expected comparison, split, merge, or report outputs.

Install this if you want an agent to process local BOM spreadsheets. Expect it to read the BOM files you provide and create Excel reports or split/merged output files, so avoid running it on sensitive supplier data unless that local persistence 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
90% confidence
Finding
Several module trigger phrases are very broad, such as generic requests like '合并BOM', '对比BOM', or '生成变更说明'. In an agent environment, this can cause the skill to activate on ordinary user messages without clear confirmation, leading to unintended file processing or report generation based on ambiguous intent.

Missing User Warnings

Low
Confidence
80% confidence
Finding
The skill states that each check should save a report file, but it does not warn the user that file creation will occur or require consent. In agent workflows, silent file creation can surprise users, clutter workspaces, overwrite outputs, or persist sensitive BOM-derived data without the user's awareness.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.