Back to skill

Security audit

智能财务报销助手(Finance Assistant)

Security checks for vulnerabilities and agentic risk

Overview

This finance-tracking skill stores invoice and reimbursement records locally and describes reminders, which is sensitive but disclosed and aligned with its purpose.

Use this skill only if you want an agent to maintain sensitive invoice and reimbursement records under ~/finance/ or a chosen finance directory. Before enabling any weekly reminder automation, confirm what it will read, whether it may update reminder counts, where summaries are delivered, and how old invoice files should be deleted or retained.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to persist sensitive financial records and invoice originals under ~/finance/ and to keep modifying those files over time, but it does not clearly warn the user that local filesystem writes and updates will occur. Because invoices and reimbursement records can contain personal and corporate financial data, silent persistence increases privacy, confidentiality, and integrity risk if the user did not explicitly authorize storage behavior.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill defines recurring weekly automation that reads financial records, increments reminder counts, and sends summaries to the user, yet it does not prominently disclose that scheduled actions and record mutations will happen automatically. Undisclosed automation over sensitive finance data can surprise users, leak information in chat contexts, and cause unintended state changes in tracking files.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The manifest description is entirely in Chinese and the rest of the skill assumes Chinese-language interaction and Chinese invoice formats, but it does not explicitly state that the locale/language is a China-specific workflow or offer user choice. Per policy, forcing a specific language without opt-in can be a natural-language policy issue unless the constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

SQP-3 applies to all file types and includes language or locale policy violations. This file presents all operational instructions and data labels only in Chinese, with no indication that users may choose another language or that the Chinese-only constraint is explicitly justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.