Back to skill

Security audit

2026税率速查:增值税企税个税申报口径

Security checks for vulnerabilities and agentic risk

Overview

This is a static Chinese tax quick-reference skill with a disclosed paid add-on promotion, and it does not contain code, hidden execution, persistence, credential access, or destructive behavior.

Install only if you want a Chinese-language mainland China tax quick reference. Treat it as a quick lookup, not professional tax advice; verify filing deadlines, local rules, and current official notices before acting. The paid SkillPay section should require your explicit confirmation before any purchase or additional skill installation.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger text is broad enough to auto-load on many ordinary tax questions, which can cause the agent to invoke this skill outside a narrowly bounded use case. In this specific file the content is informational rather than code-executing, so the main risk is misrouting, over-application of tax guidance, or unintended purchase-prompt exposure rather than direct compromise.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The invocation guidance tells the agent to use the skill for broad, everyday tax questions such as VAT rates, individual income tax, and filing deadlines without clearly limiting when the content is only a quick reference versus when authoritative, current, jurisdiction-specific verification is required. In a tax domain, over-broad triggering can cause the agent to answer compliance-sensitive questions from a static table even when facts, entity type, province, invoice type, or updated rules materially change the correct outcome.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

All user-facing descriptions, trigger phrases, and instructions are written only in Chinese, which can amount to a forced language/locale assumption under the policy if no user opt-in or justification is provided. The file does not explicitly state that the skill is intended only for Chinese-speaking users or for mainland China tax workflows as a documented locale constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The display name, description, and usage instructions are entirely in Chinese and present the skill as the default interaction mode for tax questions. There is no indication that users may choose another language or that the Chinese-only presentation is an explicit opt-in or documented locale constraint.

Content

No source excerpt is available for this finding.