Security audit

macOS截图工具免费版

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local macOS screenshot and recording helper, but its screen-capture access is sensitive and its activation guidance is too broad.

Install only if you are comfortable giving an agent command access to capture your macOS screen. Use it only for explicit screenshot or recording tasks, close or mask sensitive windows first, review output locations such as Desktop/screenshots and Desktop/recordings, and delete captures you no longer need. Treat the callback_url field as unsupported unless the publisher documents exactly what is sent and when.

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

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
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (6)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger conditions are far broader than the skill's declared screenshot/recording purpose, encouraging invocation during general coding, debugging, and deployment tasks. In an agent ecosystem, overly broad routing can cause this skill to be selected in contexts where screen capture is unnecessary, leading to excessive access to privacy-sensitive on-screen information or inadvertent recording during unrelated workflows.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: This skill performs screen capture and recording, which can collect credentials, messages, source code, tokens, customer data, and other highly sensitive information visible on screen. Without an explicit privacy warning and consent-oriented guidance, users or agents may invoke it without appreciating the sensitivity of the collected content, increasing the chance of accidental exposure or unsafe retention of captured data.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The comparison table states the free version does not support batch processing and reserves timed screenshots for the professional version. However, the later '场景三:定时截图' example implements repeated scheduled screenshots with configurable interval and count, which is the very capability the manifest says is unavailable in the free edition.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The skill introduces a callback_url and later discusses network troubleshooting even though its stated function is purely local screenshot and screen recording. In an agent context, unnecessary network-oriented parameters broaden the operational scope and can normalize sending metadata or captured results to external destinations, increasing the risk of unintended data disclosure from privacy-sensitive screen captures.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 75% confidence
Finding: The display name, summary, and the entire user-facing documentation are presented in Chinese, with no indication that users may choose another language or that the skill is intentionally restricted to a Chinese-speaking audience. This can be a language/locale policy concern when a skill appears to force a specific language without opt-in.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The feature matrix limits the free edition's image format to PNG only. Later examples and FAQ text document use of 'screencapture -t jpg' and advise converting PNG to JPEG with sips, which expands output format handling beyond the stated free-edition scope.
Content: No source excerpt is available for this finding.