Back to skill

Security audit

GPT Image 2 营销图片

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to generate marketing images as advertised, but it needs review because a custom API endpoint can receive the user's bearer API key without clear safeguards.

Review this before installing if you will use a real AI Hive API key. Use only the official AI Hive endpoint, avoid setting AI_HIVE_BASE_URL or --base-url unless you control the server, install dependencies from a trusted pinned environment, and remember that reference images are uploaded to the service and generated files are downloaded to ~/Downloads/AiHive by default.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (2)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:72
Finding

Unpinned Runtime Dependency Installation

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/imagegen.py:73
Finding

Bearer Credential Disclosure Through Unrestricted Base URL Override

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (9)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The declared purpose is narrow marketing-image generation, but the underlying implementation reportedly supports unrelated capabilities such as chat, video generation, user/account queries, file download, browser opening, and local config writes. That mismatch is dangerous because users and policy systems may authorize the skill under false assumptions, enabling privilege expansion and data access beyond the advertised use case.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The changelog content is written entirely in Chinese for multiple feature descriptions and platform notes, with no indication that language selection is optional or that the skill is intended only for a Chinese-speaking or region-specific audience. Under the policy rule for natural-language violations, this can be a locale/language constraint that is not clearly documented as opt-in or justified.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill exposes shell, network, file read/write, and environment capabilities through documented commands but declares no explicit tool scope or permissions. This weakens least-privilege guarantees and can let a seemingly simple image-generation skill perform broader actions than users or orchestrators expect if the backing scripts are modified or abused.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description lists many generic triggers such as '品牌Campaign', '活动海报', '社媒内容', and '多渠道营销资产' without clear boundaries or negative examples. This makes activation scope ambiguous and could cause unintended invocation for ordinary marketing-related requests.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The natural-language instructions are entirely written in Chinese and direct the workflow in that locale, but the skill does not state that language is optional or region-specific. This can violate language/locale policy where users should be given a choice unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The top-level docstring says the file is a '通用 AI 能力调用工具' wrapping text chat, image generation, video generation, model querying, media upload, and task polling. But the actual entry point executed by this skill is the specialized skill_main flow that fixes the model to GPT Image 2 and presents itself as a dedicated marketing-image skill. This documentation therefore describes a materially different intent than the skill file actually serves.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The module docstring and all user-facing CLI messages are written in Chinese, which effectively fixes the skill's interaction language without offering any user opt-in or alternative locale. Under the stated policy, forcing a specific language is a natural-language policy violation unless the locale constraint is explicitly justified or optional.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The manifest describes a focused skill for generating a set of GPT Image 2 marketing images. However, the shipped skill interface also includes separate task and upload subcommands, letting users query arbitrary generation tasks and upload media independently of marketing image creation. Those capabilities go beyond the narrow generation purpose stated in the manifest.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The sample API key value includes Chinese text ('请替换为你的APIKey'), which imposes a specific language in user-facing configuration content. This can violate language/locale policy when no alternative language choice or justification is provided.

Content

No source excerpt is available for this finding.