Security audit

Plans & Todos

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward local planning helper that stores plans and todos in a disclosed local Markdown file without executable code, networking, or hidden privileged behavior.

Install this if you want a persistent local plans and todos file. Do not store passwords, keys, or highly sensitive personal details in it, and ask the agent to confirm before saving new plans or marking tasks complete if you want tighter control.

A.I.G

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

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (4)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill description uses very broad trigger terms like goals, tasks, plans, and roadmaps, which overlap with ordinary conversation and can cause the skill to activate in situations where the user did not intend persistent planning behavior. In this context, unintended activation is risky because the skill is designed to read and modify a persistent local file, increasing the chance of surprise data storage or unintended edits.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The skill persistently stores information in ~/.openclaw/workspace/memory/plans-todos.md and even instructs creating the directory if it does not exist, but it does not clearly notify the user at the point of action that data will be written locally. This creates a privacy and consent issue: users may disclose personal goals or task details without realizing they are being retained on disk.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The instruction to automatically update tasks whenever the user says they completed something is ambiguous and may treat casual conversation as an authorization to modify persistent records. Because the skill performs stateful updates, an imprecise completion trigger can lead to incorrect task completion, loss of tracking integrity, and silent modification of user data.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: The natural-language instructions and examples are presented in Chinese, which may impose a language preference on users without any opt-in or documented reason for the locale constraint. Under the stated policy, language-specific behavior should either offer user choice or clearly justify the restriction.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.