Back to skill

Security audit

万能财务会计技能包

Security checks for vulnerabilities and agentic risk

Overview

This is a finance/accounting guidance skill with sensitive but purpose-aligned workflows and no code, network access, persistence, or hidden behavior.

Install only if you want Chinese-language accounting and spreadsheet assistance. Because the workflows can involve tax IDs, bank statements, invoices, and ledgers, redact or mask unnecessary sensitive data and confirm before allowing changes to production financial records.

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
  • 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 (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill is designed for accounting, tax, invoice, bank reconciliation, and financial reporting, all of which commonly involve highly sensitive business and personal data. Without an explicit warning or data-handling notice, users may provide tax IDs, bank details, invoice numbers, or confidential ledgers without understanding the sensitivity or minimizing disclosure.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill activates on essentially any finance or accounting request, creating a high chance of over-triggering in contexts where the user did not intend to invoke this specialized workflow. In a domain involving sensitive financial, tax, invoice, and banking data, broad activation increases the risk of unnecessary exposure of confidential information and inappropriate automation guidance.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

Several trigger phrases in the Excel automation section are overly generic, such as requests to fill forms, generate reports, summarize data, or automate calculations. These phrases can match many unrelated user intents and may cause the skill to engage on sensitive spreadsheets or financial records without sufficient certainty or consent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The manifest description, trigger phrases, templates, and workflow instructions are presented entirely in Chinese, with no indication that users may choose another language. Under the stated policy, a fixed language without opt-in can be a natural-language locale violation unless explicitly justified.

Content

No source excerpt is available for this finding.