Security audit

Grok图片生成-专业版

Security checks for vulnerabilities and agentic risk

Overview

This skill is an image-generation workflow helper, but it asks for broad command/file authority and includes external sending and browser-session automation with loose scoping.

Review this skill before installing if you do not want broad local command/file access, browser automation against a logged-in Grok account, or generated images sent to Feishu or callbacks. Use it only with explicit output directories and confirmed messaging destinations, and avoid giving it unrelated automation tasks.

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 (5)

Context-Inappropriate Capability

Medium

Confidence: 94% confidence
Finding: The skill advertises generic command execution and information-retrieval capabilities that are much broader than its stated purpose of image generation and workflow automation. In an agent context, unnecessary broad capabilities increase the chance of misuse, prompt-triggered overreach, or execution of unrelated local/system actions beyond user expectations.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The activation guidance is framed around broad productivity and automation use cases instead of narrowly scoped image-generation tasks. Overbroad invocation language can cause an agent to select this skill in unrelated contexts, exposing file write, exec, and external messaging behaviors when the user did not intend them.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The coverage keywords massively expand the skill's apparent applicability, including vague terms like efficiency, automation, and workflow optimization. In an auto-routing environment this can trigger the skill far outside its intended domain, increasing the likelihood of unnecessary command execution, file operations, and third-party data transmission.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill promotes sending generated images to external messaging platforms but does not clearly warn about privacy and data-sharing implications. Users may unknowingly transmit sensitive prompts or generated content to third-party services, especially in automated batch workflows.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill promotes sending generated images to external messaging platforms but does not clearly warn about privacy and data-sharing implications. Users may unknowingly transmit sensitive prompts or generated content to third-party services, especially in automated batch workflows.

Static analysis

No suspicious patterns detected.