ClawHub
Back to skill

Security audit

US Quote Builder

Security checks for vulnerabilities and agentic risk

Overview

The bundled skill has limited local access, but its quote calculations and supplied template need correction before customer use.

Use a dedicated output folder because estimate.md is overwritten. Correct the template/script mismatch and independently verify amounts, applicable tax, margin, and expiration before sending any quote. The optional Windows executable is unnecessary for this workflow and requires a separate trust decision; the supplied hash does not establish its safety.

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
95% confidence
Finding

The code supports the core estimate-building purpose, but materially omits two advertised quote features: functional margin handling and a stated validity date. Sales tax is implemented only as a fixed rate applied to every amount, without jurisdiction or taxability handling. Local CSV reading and Markdown output are supporting implementation details; no unrelated capabilities or external resource access are evident.

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.

Generated quotes omit the promised validity date and do not calculate margin.

Low
Category
Excessive Agency
Confidence
97% confidence
Finding

The manifest promises a quote with margin and a stated validity date. The implementation only prints a target-margin constant, calculates subtotal plus tax without applying or deriving margin, and writes the report without any validity date.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.