ClawHub
Back to skill

Security audit

智标领航投标文件自动生成

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed cloud-based bid-document assistant that uploads user-selected tender files to a named service and stores credentials locally.

Install only if you are comfortable sending tender and bid documents to biaoshu.zhiliaobiaoxun.com under your App Key account. Do not paste the App Key into chat; create the local config file yourself, and confirm before each document upload or paid generation step.

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
91% confidence
Finding
The activation rule is unusually broad: it says the skill must be used for essentially any bidding or tender-document-related request, even if the user did not explicitly ask for this skill. In context, the skill uploads sensitive tender/bid documents to a remote service and may incur account charges, so overbroad triggering can cause unintended data transfer, privacy exposure, or billed actions without sufficiently specific user intent.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill acknowledges that user-provided tender and bid documents are uploaded to an external server, but the warning is framed as a first-use notice rather than a mandatory precondition before every upload-bearing operation. Because these files may contain confidential commercial, pricing, or personal data, inconsistent consent gating can lead to users unknowingly sending sensitive documents off-device, especially when the skill aggressively auto-applies to related requests.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.