Security audit

任务

Security checks for vulnerabilities and agentic risk

Overview

This Tasker task-management skill is not clearly malicious, but it requests broad read, write, and command execution authority without tight task-specific scoping.

Review this skill before installing if you only need simple Tasker task lists. It should be used only when you are comfortable granting an agent broad local read/write and command execution tools, and you should avoid providing credentials or file paths unless the action is clearly Tasker-specific and user-directed.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Context-Inappropriate Capability

High

Confidence: 94% confidence
Finding: The skill exposes broad read/write and external API capabilities that are not clearly justified by the stated Tasker purpose. In an agent environment, that overbroad capability set can enable unintended file modification, sensitive file access, or unreviewed outbound data transfer if the skill is activated on loosely related prompts.

Context-Inappropriate Capability

Medium

Confidence: 94% confidence
Finding: The skill exposes broad read/write and external API capabilities that are not clearly justified by the stated Tasker purpose. In an agent environment, that overbroad capability set can enable unintended file modification, sensitive file access, or unreviewed outbound data transfer if the skill is activated on loosely related prompts.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The activation language is very broad ('improve efficiency', 'automation', 'batch processing', 'workflow optimization'), which can cause the skill to trigger for many unrelated requests. When combined with powerful tools like read/write/exec, overbroad matching increases the chance that the skill gains access in contexts where its dangerous capabilities are unnecessary or unexpected.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The documentation mentions file writing, API calls, and command execution without clearly warning that the skill may modify files, contact external services, or run system commands. In an agent setting, lack of transparent disclosure undermines informed consent and can lead users to invoke the skill without realizing it may alter the system or exfiltrate data.

Static analysis

No suspicious patterns detected.