Back to skill

Security audit

Paper Reading Problem Reality Check

Security checks for vulnerabilities and agentic risk

Overview

This skill is a structured research-review workflow that reads and writes local research artifacts, with no evidence of hidden execution, credential use, network retrieval, or destructive behavior.

Before installing, expect this skill to read existing local research-question and field-map artifacts and to create or update review files under the workspace. It should be used on research workspaces you are comfortable sharing with the agent, but there is no artifact-backed sign of hidden network access, credential handling, or unsafe automatic execution.

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