ClawHub
Back to skill

Security audit

auto-repair-invoice-explainer

Security checks for vulnerabilities and agentic risk

Overview

The bundled script performs local text checks without evident harmful behavior, but it does not produce the promised invoice explanations.

Expect a text-checking report, not invoice calculations or explanations. Review charges yourself, omit unnecessary customer details, and use an output folder where replacing lint-report.md is acceptable. The optional unsigned Windows application is separate and is not covered by this assessment.

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
99% confidence
Finding

The declared description promises customer-facing invoice interpretation, but the implementation only performs keyword and formatting checks on existing text. Its section checks use substring matching rather than parsing invoice structure or amounts. Reading an input file and writing a report are supporting implementation details, not separate security concerns; the mismatch is the materially different primary purpose.

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 skill performs copy linting rather than explaining an auto repair invoice.

Medium
Category
Excessive Agency
Confidence
100% confidence
Finding

The manifest promises a plain-language breakdown of invoice labor, parts, fees, and taxes. The implementation only checks for section keywords, long lines, and banned phrases, then writes a lint report; it does not interpret invoice charges or produce customer-facing explanations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.