Back to skill

Security audit

Paper Polisher

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown prompt skill for academic paper polishing, with no tool use, persistence, credential handling, network access, or local file authority.

Safe to install for paper-polishing workflows. Users outside Chinese-language contexts or outside civil/vibration engineering should check whether the prompt should be adapted to their preferred language and discipline before relying on terminology edits.

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
93% confidence
Finding

The skill title and description present the skill entirely in Chinese and frame it as a Chinese-language paper polishing expert, without stating that users may choose their preferred interaction language. Because the policy applies to natural-language constraints across all file types, this is a locale/language preference issue rather than a functional limitation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
72% confidence
Finding

The English-paper prompt defines the role specifically as a senior expert in civil engineering and vibration engineering, while the broader skill description claims support for SCI papers generally. This natural-language constraint may inappropriately steer responses toward a specific domain for users outside that field without warning or choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.