Back to skill

Security audit

gp-rejection-decision-support

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Chinese government-procurement decision-support skill with disclosed knowledge-base lookup behavior and no executable or persistent components.

Before installing, users should understand that this skill is tailored to Chinese government procurement evaluation work and may produce consequential draft reasoning. Treat outputs as decision support only, verify cited legal provisions and knowledge-base sources against current official materials, and keep final invalid-bid or clarification decisions with the legally authorized evaluation committee or counsel.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The README presents all user-facing instructions and capability descriptions only in Chinese, and does not indicate that the skill is limited to Chinese-speaking users or provide an opt-in language choice. Under the policy, forcing a specific language without user choice or clear justification 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
92% confidence
Finding

Line L03 states that the file must be used entirely with government-procurement-law terminology, and the file overall is written exclusively in Chinese. This imposes a specific language/locale mode without offering the user any choice or opt-in, which matches the language/locale policy violation category.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

标题与开头内容直接以中文并面向“政采专家版”展开,但未说明该语言/地区限定是否为面向特定用户群的设计选择,也未提供语言切换或用户选择。按规则,强制特定语言或 locale 且无用户 opt-in,属于自然语言层面的策略违规风险。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The display name is entirely in Chinese, which signals a fixed language choice in the skill metadata. Because the manifest does not mention any language selection, opt-in, or region-specific justification, this appears to impose a locale preference rather than offering a user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

Line L03 states that the file "统一使用政采术语" and the entire document is written as a fixed Chinese wording template set, which effectively forces one language/locale style. Under the policy rule, language constraints should either be optional for users or clearly documented as justified for a region-specific compliance purpose.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.