Back to skill

Security audit

police-NERRE

Security checks for vulnerabilities and agentic risk

Overview

This skill is a transparent Chinese police-incident text extractor that handles sensitive personal data but does not include code, hidden execution, persistence, or data exfiltration behavior.

Install only if you are authorized to process the police-incident text you provide. Because the skill can surface highly sensitive personal data in structured JSON, use it in an approved workflow and avoid pasting data that should not be processed or retained by your agent environment.

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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description and instructions require a fixed Chinese JSON schema and Chinese output terms, but the file does not offer language/locale opt-in or explain that the skill is intentionally limited to a Chinese policing context. This is a natural-language locale policy concern under SQP-3.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly directs extraction of highly sensitive personal data such as ID numbers, phone numbers, bank card numbers, and location information, but provides no privacy safeguards, consent requirements, minimization rules, or handling restrictions. In a police-incident context this materially increases the risk of unauthorized collection, overexposure, and downstream misuse of regulated personal data.

Content

No source excerpt is available for this finding.