Back to skill

Security audit

Invoice Compliance Checker

Security checks for vulnerabilities and agentic risk

Overview

This skill does not show malware-like behavior, but its invoice-checking purpose is blurred into broad financial and tax advice.

Review this skill before installing if you expect narrow invoice-compliance help. It appears non-executing and non-exfiltrating, but it may be selected for broader financial, tax, or budgeting questions and may give generic advice without clear jurisdiction or locale boundaries.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (7)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger section significantly exceeds the stated purpose of an invoice compliance checker and invites use for broad financial advisory tasks such as budgeting, pricing, tax deductions, and financial health analysis. In an agent-routing context, this can cause the wrong skill to be selected for sensitive financial requests, producing misleading compliance-flavored output outside its competence and weakening downstream safety, quality, and policy controls.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description and examples are predominantly written in Chinese, while also including some English, but there is no statement offering a language choice or explaining that the skill is intentionally limited to Chinese-speaking users. This can violate a language/locale policy when a skill appears to impose a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The metadata declares the skill as English-only, but the content includes Chinese-language, China-specific invoice-verification guidance. This inconsistency can cause improper routing, localization failures, or incorrect assumptions about supported jurisdictions and languages, which is especially risky in a compliance-oriented skill where legal and procedural advice is locale-dependent.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The top-level docstring describes a generic descriptive skill, while the implementation later identifies itself as an "Invoice Compliance Checker" and generates domain-specific compliance recommendations based on tax, legal, and international cues. This is an active contradiction in documented intent versus implemented behavior, not merely an omitted detail.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger list contains generic terms such as "invoice," "compliance," and "checker," which are likely to match many unrelated user requests and cause unintended activation of this skill. In an agent environment, overbroad routing can lead to incorrect handling of user data or actions, especially for finance-related tasks where context accuracy matters.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The acceptance criteria state 'Clear documentation in English,' which imposes a specific language requirement in natural language. Under the policy, forcing a language without user opt-in or a documented justification can be a locale-policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest sets "language": "en", which imposes a specific language preference, but there is no indication that users can opt into other languages or that English-only behavior is required for a documented regional or compliance reason. This can violate language or locale policy expectations for user choice.

Content

No source excerpt is available for this finding.