横幅插画生成免费版

• Outcome: Review
• Latest audit: Aug 17, 2026 · 1:22 AM UTC
• Version: 1.0.3

Overview

The skill is mainly an image-generation guide, but it asks for execution/write authority while giving broad and inconsistent automation instructions beyond that purpose.

Review this skill before installing. It appears to be a Markdown-only image-generation guide, not a working packaged tool, and its instructions are broader than banner generation. Prefer using environment variables for API keys, avoid passing secrets on the command line, and only allow exec/write use for clearly identified image-generation commands you trust.

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (6)

Description-Behavior Mismatch

Medium

• Confidence: 93% confidence
• Finding: The manifest and top-level description present the skill as a banner/image-generation tool, but the text broadens activation to API integration, webhook configuration, system connection, and generic automation tasks. This scope inflation can cause an agent to invoke a tool with exec/write capability in contexts far beyond its documented purpose, increasing the chance of unintended command execution or misuse.

Intent-Code Divergence

Medium

• Confidence: 90% confidence
• Finding: The documentation claims support for create/query/modify/delete and import/export/reset style operations through generic parameters, but the rest of the skill only shows image generation/editing flows. This misleading capability expansion can prompt an agent or user to treat the skill as a general-purpose automation interface and supply unsafe inputs to exec-backed workflows.

Intent-Code Divergence

Medium

• Confidence: 85% confidence
• Finding: The skill says the free version only supports single-image generation/editing, yet later markets batch processing, file parsing, multi-interface aggregation, and repeated task automation as if built in. These contradictions weaken operator trust boundaries and may cause overbroad invocation of a skill that also has exec/write access.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The invocation language is overly broad for an image-generation skill, telling agents to use it for API integration, interface docking, webhooks, and system connections. In an agent environment, broad triggers can cause unnecessary activation of a tool with execution capability in unrelated tasks, expanding attack surface and creating tool-confusion risks.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The keyword coverage list is excessively broad and ambiguous, effectively turning descriptive text into catch-all activation triggers. This makes accidental or inappropriate invocation more likely, especially when the skill has access to exec/write and can influence local system state.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The documentation explicitly encourages passing the API key via a command-line parameter without a warning that CLI arguments may be exposed through shell history, process listings, logs, or telemetry. This can directly leak credentials in multi-user systems, CI environments, agent logs, or debugging output.

VirusTotal

VirusTotal findings are pending for this skill version.

Static analysis

No suspicious patterns detected.