Back to skill

Security audit

国企采购评审专家

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language PRC state-owned-enterprise procurement compliance skill with no executable code, persistence, credential use, or hidden data handling found.

Install this only for PRC state-owned-enterprise procurement and tendering questions. Treat outputs as compliance guidance rather than formal legal advice, verify current law and local rules, and be aware that the skill is written for Chinese-language use and depends on disclosed external ima knowledge bases for richer sourcing.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (8)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest description and core overview present the skill entirely in Chinese and position it as serving users nationwide, but nowhere offers a language choice or states that responses can adapt to user preference. Under the policy rule, forcing a specific language/locale without opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The manifest description states the skill is based on the legal framework of the People's Republic of China and state-owned enterprise procurement rules. For a general-purpose skill manifest, this imposes a jurisdiction-specific policy context without explicitly limiting the skill to that region or giving users a choice, which can create a locale/policy mismatch.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

Lines L33-L35 require the assistant to use a fixed Chinese disclaimer whenever the connector is unavailable. This is a natural-language locale constraint presented as mandatory behavior, and the file does not offer the user any language choice or explain that the skill is intentionally limited to Chinese-only operation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The fallback templates in L52-L56 are written as required quoted responses and do not provide an option to adapt to the user's preferred language. This forces a specific locale in natural-language behavior, which violates the stated policy unless choice or justification is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The title and procedural instruction are entirely in Chinese and direct the responder to follow this framework upon receiving a question, which effectively imposes a specific language/locale on outputs. The file does not indicate that Chinese is optional, user-selected, or limited to a clearly documented region-specific deployment.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file instructs that when a user uses an incorrect term, the assistant 'must first correct and then answer,' and the entire guidance is framed exclusively in Chinese terminology conventions. Because the file does not offer a language or locale choice or state that this behavior applies only when the user wants Chinese procurement-law terminology, it imposes a specific language/locale behavior without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The README presents the skill entirely in Chinese and does not indicate that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The entire skill file is written in Chinese and does not indicate that language selection is optional or that the skill is explicitly limited to Chinese-speaking users. Under the policy rule for natural-language violations, forcing a specific language without user opt-in can be a locale-policy issue.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.