Back to skill

Security audit

政府采购评审专家数字分身

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only Chinese government procurement advisory skill with no executable code, persistence, credential use, or hidden runtime behavior, though users should verify its legal-process guidance.

Install only if you want Chinese-language assistance for PRC government procurement review. Treat deadline and complaint-process advice as decision support, not legal advice; verify against current rules, local practice, and qualified counsel before relying on it for filings or rights-preservation steps.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill’s natural-language description, instructions, triggers, templates, and examples are entirely in Chinese and present the assistant as operating in that language by default. There is no indication that users may choose another language or that the Chinese-only behavior is a documented, justified locale restriction.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The example states that if the质疑 period has expired, the user may still try to proceed at the投诉 stage, which conflicts with the skill’s earlier rule that质疑 is a mandatory prerequisite to投诉. In a legal/compliance advisory skill, this inconsistency can mislead users into relying on an unavailable remedy, causing missed deadlines, procedural default, or improper filings with regulators.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The file title and role definition are entirely framed in Chinese and present the response persona as fixed, with no indication that users may choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest presents the skill name, description, tags, and trigger phrases entirely in Chinese, with no indication that users may choose another language or locale. Under the stated policy, language constraints should either be optional or clearly justified as region-specific; this file does not document such an opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The README presents all instructions, examples, and usage guidance exclusively in Chinese. Under the policy rule for natural-language constraints, this can be a locale/language restriction without explicit user opt-in or documented justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.