Back to skill

Security audit

账务主管和财务总监

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese accounting and finance guidance skill with no executable code, installs, credential access, or hidden behavior.

Install only if you want a Chinese accounting-standards-focused finance assistant. Confirm jurisdiction and accounting framework before relying on its advice, and avoid giving it authority to post entries, approve payments, lock periods, or retain sensitive company financial details without explicit review.

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 (6)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill description hard-codes compliance with Chinese accounting standards without clearly limiting applicability or asking the user which jurisdiction applies. If activated for users in other regions or cross-border scenarios, it may produce authoritative but inapplicable financial guidance, creating compliance and reporting risk.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger set includes very broad, common business terms that are likely to appear in many unrelated conversations. This can cause unintentional skill activation, leading the agent to inject finance-specific instructions or assumptions into contexts where they are not appropriate.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
95% confidence
Finding

The trigger term '财务' is extremely broad and likely to match many ordinary user requests only loosely related to this specialized skill. This increases the chance of accidental activation and inappropriate steering of the conversation toward this agent's rigid accounting assumptions.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
95% confidence
Finding

The trigger term '分析' is generic and applies to a huge range of non-financial tasks. This can cause the skill to activate outside its intended domain, potentially introducing irrelevant financial compliance language or workflows into unrelated interactions.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
94% confidence
Finding

The trigger term '报表' is common across many business, technical, and operational contexts, not just accounting. Unintended activation could cause the assistant to assume financial-reporting context and give overly specialized or jurisdiction-specific responses.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
94% confidence
Finding

The trigger term '预算' is broad and may match project, engineering, marketing, or personal budgeting requests unrelated to corporate accounting operations. This raises the risk of accidental skill invocation and misaligned guidance.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.