Back to skill

Security audit

Expense Approval Workflow Designer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple local expense-workflow template generator with no hidden network, financial, or persistence behavior found.

Reasonable to install for informational workflow design. Treat its recommendations as templates rather than financial or accounting advice, and note that it runs a local Python handler to produce JSON even though the docs phrase this as no real code execution.

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
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The module documentation says 'No real code execution or financial transactions,' which contradicts the actual behavior in the file: it defines executable functions, processes user input, and returns generated output. While the code does not execute external commands or financial transactions, the phrase 'No real code execution' is inaccurate for a handler that clearly runs logic.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The inline comment on L110 includes Chinese text ('其他skill类似') even though the file otherwise uses English and provides no indication that multilingual output or documentation is intentional. This creates an undocumented language choice in the skill file, which can conflict with organizational language/locale expectations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest sets the skill language to "en", which is a natural-language locale constraint. Under the policy, forcing a specific language without user opt-in or a clear region-specific justification is a violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.