Back to skill

Security audit

政采评审专家“判例法”指引

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow Chinese government-procurement review aid with disclosed knowledge-base use and no executable code, persistence, or hidden access behavior.

Installers should understand that this is a Chinese-language, China government-procurement legal/compliance aid. It should be treated as decision support only: verify cited laws and knowledge-base results, and do not use it as a substitute for formal legal or procurement authority 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
  • 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 (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The README is entirely written as a Chinese-only skill description and presents outputs, examples, and operating assumptions solely in Chinese. There is no indication that users may choose another language or that the language restriction is an explicit, justified policy requirement, which can violate language/locale choice expectations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The instruction says outputs must uniformly use specific Chinese terms and must not use alternative terminology. This imposes a language/locale constraint in the skill's natural-language behavior without indicating user choice or opt-in, which matches the policy-violation category for forced language or locale.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The display name and full description are written only in Chinese, and the manifest does not indicate that the skill is China-region-specific or that users may opt into another language. This can violate language/locale policy when a skill effectively requires one language without explicit user choice or documented justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. This markdown file presents all instructions and operational guidance only in Chinese, with no statement that the skill is China-specific or that users can opt into the language, which can amount to forcing a language/locale without user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file contains user-facing instructional content only in Chinese, which can amount to a language/locale policy violation when the skill does not provide opt-in or alternative language support. The file does not state that it is intentionally limited to a Chinese-speaking or region-specific audience, so the language constraint is not explicitly justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.