Back to skill

Security audit

Paper Reading Method Commitment

Security checks for vulnerabilities and agentic risk

Overview

This skill is a structured research-method workflow that reads and writes local project notes with clear user checkpoints and no hidden execution behavior.

Installing this should mainly affect your workspace notes: it will guide the agent to read relevant local research artifacts and create or update method-commitment files. Review the chosen workspace root before use, especially if you point it at an existing project, because the workflow is designed to update existing artifacts rather than only create new ones.

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