ClawHub

inventory-anomaly

Security checks across malware telemetry and agentic risk

Overview

This skill is a local inventory forecasting template that reads and writes project Excel/report files, with no evidence of hidden network access, credential use, or destructive behavior.

Install this only in a dedicated project or virtual environment. Review and pin dependencies for production use, and back up any real inventory workbook before running scripts that generate or write data/spare_parts.xlsx.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill instructs creation and use of modules that read and write Excel files and output reports, but it does not declare any corresponding permissions. This creates a trust and containment gap: an agent or platform may execute file operations that users and policy controls did not explicitly authorize, increasing the risk of unintended access to local data or overwriting files.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The activation description is very broad and can match many ordinary inventory, forecasting, reporting, or Excel-related requests. Over-broad triggering can cause the skill to activate in contexts the user did not intend, leading to unnecessary file access, code generation, or operational guidance being applied to the wrong task.

Natural-Language Policy Violations

Medium
Confidence
80% confidence
Finding
The skill metadata and content are written to operate in Chinese without documenting a locale constraint or obtaining user preference. Forced language behavior can cause misunderstandings around generated code, reports, parameters, or operational steps, which is especially risky in business workflows involving inventory decisions and anomaly handling.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal