Security audit

任务守望者与弹窗杀手 (Task Watchdog)

Security checks for vulnerabilities and agentic risk

Overview

This skill is disclosed as a task watchdog, but it gives the agent broad unattended control over the user's screen and may dismiss important system or security warnings.

Install only if you are comfortable letting the agent watch and click in your active desktop session while you are away. Use it on non-sensitive machines or isolated sessions, avoid configuring webhook screenshots unless you control the endpoint, and do not rely on it around antivirus, update, permission, crash, storage, or memory warnings.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (1)

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:33
Finding: Autonomous Dismissal of Security-Sensitive and System Dialogs
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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

Findings (3)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill explicitly instructs automated dismissal of system and application popups, including security-relevant dialogs such as update prompts, memory warnings, and antivirus messages. Even though a caution appears later, the core behavior still authorizes UI actions that can suppress important warnings, cause misclicks, or interact with privileged/system dialogs without reliable verification of safety.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill permits sending alerts via webhook after taking a full-screen screenshot, but it does not clearly warn that sensitive on-screen content and system state may be transmitted over the network. This creates a data exposure risk because screenshots can contain credentials, personal data, proprietary work, or unrelated application content.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The file's natural-language description forces Chinese-language interaction/presentation, and no user opt-in or locale justification is provided. Under the policy rule, unqualified language restriction is a natural-language policy concern.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.