Back to skill

Security audit

Writing Style Dankoe

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only writing-style guide that changes prose style and does not request access to files, credentials, tools, or the network.

Install this skill if you want the agent to produce essays in this specific reflective, framework-heavy style. Expect it to bias phrasing and examples toward natural Chinese expression when used for Chinese output, but it does not add executable behavior or request sensitive access.

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
95% confidence
Finding

Line L016 instructs that when using this style, Chinese output should be adapted to Chinese expression habits and analogies. This imposes a specific language/locale behavior in the skill instructions without indicating that users may choose another language, which matches the policy concern for forced language constraints.

Content

No source excerpt is available for this finding.