ClawHub
Back to skill

Security audit

inventory-tracker

Security checks for vulnerabilities and agentic risk

Overview

The advertised inventory calculator silently loses item identifiers and omits calculations, making its results unreliable for business decisions.

Use copies of your records and independently check identifiers and reorder quantities; the current script needs correction before operational use. Verify its tax guidance: the claimed LIFO repeal conflicts with [IRS Form 970 guidance](https://www.irs.gov/forms-pubs/about-form-970). Assess the optional unsigned Windows application separately; it is unnecessary for the Python workflow.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

If the reported script behavior is accurate, replacing nonnumeric SKUs with zero corrupts item identity, while missing calculations and adjustment records undermine the inventory integrity the skill promises. In a warehouse workflow, this can misassociate records, produce unreliable replenishment decisions, and compromise audit trails; however, the script was not supplied, so these implementation claims cannot be independently verified.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The script claims to compute a reorder point but only prints inputs and the formula.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The script advertises a reorder-point calculation but never evaluates the formula or outputs a reorder_point_qty; it produces only normalized inputs and formula text. In an inventory-planning workflow, this misleadingly incomplete output could lead users or downstream agents to make replenishment decisions without a computed threshold, risking stockouts or excess purchasing. This is an operational-integrity defect, not evidence of malicious execution or data exfiltration.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.