Back to skill

Security audit

第三人称 NoFlatter · Anti-Sycophancy / 第三人称改写

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-reframing skill that asks the agent to answer more neutrally when the user explicitly enables it.

Installers should expect this skill to make answers more neutral and less validating when invoked. It does not appear to add technical access or persistence, but users who want a warmer response style may prefer not to enable it for sensitive conversations.

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