Back to skill

Security audit

reply-polish

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese workplace reply-polishing skill with no code, network access, persistence, or hidden system access.

Install this if you want help polishing Chinese workplace replies. It is intentionally scoped away from English drafts, from-scratch writing, and general communication frameworks, so use another writing skill for those cases.

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 (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest text repeatedly states that the skill only handles Chinese drafts and excludes English, which is a language constraint expressed in natural language. Under the policy rule, forcing a specific language without user opt-in can be a locale/language policy violation unless the restriction is explicitly justified as region-specific or optional.

Content

No source excerpt is available for this finding.