Back to skill

Security audit

de-ai-flavor

Security checks for vulnerabilities and agentic risk

Overview

This Chinese Markdown editing skill is narrowly scoped and disclosed, but users should know it edits the target file directly before showing a diff.

Install this if you want an agent to polish Chinese Markdown files for AI-like phrasing. Because it writes changes directly before showing the diff, use it on files you can review or restore, such as files under version control.

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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly states it will directly modify the user-specified file and only show a diff afterward, which means destructive changes can occur before the user has a chance to review or approve them. In a file-editing skill, this creates a real safety issue because an incorrect rewrite, path mistake, or overbroad edit could alter important content without informed consent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The natural-language description repeatedly constrains the skill to Chinese content and Chinese stylistic norms, but it does not present this as an opt-in language choice or clearly justify it as a locale-specific tool. Under SQP-3, forcing a specific language without user opt-in can be a policy violation.

Content

No source excerpt is available for this finding.