Back to skill

Security audit

Planner

Security checks for vulnerabilities and agentic risk

Overview

This planner skill stores user-created planning data locally in disclosed JSON files and does not show hidden networking, unsafe execution, or deceptive behavior.

Install this only if you are comfortable with plans being saved locally across sessions. Avoid storing secrets or highly sensitive personal details in plans, and periodically review or delete the planner JSON files if retention matters to you.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill advertises local file persistence and references multiple scripts that read and write plan data, but it does not declare any explicit tool scope or permissions boundary. That creates an authorization ambiguity where the runtime may grant broader file access than users or reviewers expect, increasing the risk of unintended reads or writes to local data.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
88% confidence
Finding

The skill explicitly maintains persistent local storage for plans and archives, which means potentially sensitive user goals, schedules, budgets, and project details can remain on disk across sessions. Even without network exfiltration, session persistence increases privacy and confidentiality risk if data is retained longer than expected or accessed by other local processes or users.

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: planner
description: Local-first planning engine for trips, weeks, launches, projects, schedules, and structured decision-making. Use whenever the user wants to plan something, organize future steps, create a roadmap, map constraints, compare options, or turn a vague goal into a phased plan. Also use when the user says they need a plan, itinerary, schedule, rollout, timeline, or structured next steps. Local-only storage.
---

# Planner: Turn uncertainty into a workable plan.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The activation text is extremely broad, triggering on generic requests like needing a plan, roadmap, schedule, or structured next steps. Over-broad routing can cause the skill to be invoked in contexts the user did not intend, leading to unnecessary data capture or file persistence of sensitive personal, project, or scheduling information.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.