Back to skill

Security audit

胡田 OPC导师 政策工具包

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a legitimate policy-application helper, but it works with sensitive business, identity, payroll, bank, and credit materials without clear handling limits.

Install only if you are comfortable using it for China-focused policy申报 workflows. Before providing documents, redact unnecessary personal data, avoid sharing full bank or credit records unless required, confirm whether web access is needed, and decide where generated reports should be stored or deleted.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation instruction says users can 'directly describe the current application scenario' to trigger the skill, but it does not define scope boundaries, required confirmations, or limits on autonomous actions. In a skill that later describes network access, material generation, and handling of enterprise application data, this can cause the agent to begin collecting, processing, or acting on sensitive information without clear user consent or constrained execution.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This section instructs collection and use of sensitive enterprise materials such as ID documents, financial reports, social security records, bank account proofs, and credit reports, but provides no privacy notice, retention policy, minimization guidance, or handling constraints. That creates a real risk of over-collection and unsafe exposure of business and personal data if the skill is used as written.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The harness explicitly describes testing network connectivity, visiting policy websites, generating local files, and performing self-healing retries, yet none of these capabilities are disclosed to the user in a consent-oriented way. Hidden or under-disclosed external access and file generation increase the chance of unintended data transmission, persistence of sensitive content, and surprise side effects during execution.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The file presents the skill description and usage instructions entirely in Chinese, and there is no indication that users may select another language or that the skill is intentionally limited to a Chinese-speaking or region-specific audience. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The visible natural-language content, including title, description, usage instructions, and operational guidance, is entirely in Chinese, and the file does not offer a user language/locale choice. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy concern unless the locale restriction is clearly justified.

Content

No source excerpt is available for this finding.