Security audit

Invoice Chaser CN

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple invoice-reminder writing aid with no code execution, persistence, or hidden data access.

Before installing, note that the skill asks for invoice and client payment context so it can draft reminders. Review any generated collection message before sending, especially in disputed or legally sensitive situations, and adjust the language if you do not want bilingual output.

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

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (3)

Natural-Language Policy Violations

Medium

Confidence: 89% confidence
Finding: The description states the skill automatically generates Chinese-English bilingual collection messages, which imposes a language behavior by default. The file does not indicate that users can choose a single language or opt into bilingual output, so it conflicts with the policy against forcing a specific language or locale without user choice.

Natural-Language Policy Violations

Medium

Confidence: 92% confidence
Finding: The output requirements explicitly require both the email body and IM short message to be produced in Chinese and English. Because no alternative language-selection path is described, this reads as a forced language policy rather than an opt-in preference.

Natural-Language Policy Violations

Medium

Confidence: 87% confidence
Finding: The example prompt tells the assistant to generate the email body and IM messages in both Chinese and English, reinforcing a mandatory language behavior. There is no accompanying note that the user may select a preferred language, so this is a natural-language policy issue.