Security audit
Agent Plan Manager
Security checks for vulnerabilities and agentic risk
Overview
This skill is a lightweight Markdown planning helper that creates and updates task plan documents, with no hidden execution, credential use, or persistence beyond the disclosed plan files.
Installers should expect the agent to create and maintain Markdown planning files in the workspace. Review generated plans if they include sensitive task details, URLs, or implementation notes, but the artifact itself does not request credentials, background execution, or broad system 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
