Security audit

GPT Image 2 直播带货图片

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches its image-generation purpose, but it needs review because it stores and uses an AI Hive API key and can send that key to an arbitrary configured API endpoint.

Review this skill before installing if you will use a real AI Hive API key. Use the default AI Hive endpoint unless you intentionally trust a custom endpoint, protect ~/.ai-hive/config.json from modification, avoid uploading non-image or sensitive files, and consider pinning dependencies before installation.

A.I.G

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 Third-Party Dependency Installation
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/imagegen.py:91
Finding: Unrestricted Base URL Override Can Expose API Credentials
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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

Findings (10)

Context-Inappropriate Capability

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: Video generation is a materially broader capability than the declared image-only livestream asset generation and permits uploading image, video, and audio inputs plus retrieving generated media. This unnecessary capability expansion significantly increases misuse potential, operational cost exposure, and the chance that an agent can perform actions outside the approved scope.
Content: No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 92% confidence
Finding: The skill invokes shell commands, installs a package, and uses a Python script that likely performs file, environment, and network operations, but it declares no explicit tool scope or permission boundaries. This creates unnecessary privilege exposure: an agent may grant or assume broader capabilities than needed, increasing the blast radius if the script is modified, compromised, or triggered in an unexpected context.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The manifest description says to use this skill for a long list of generic livestream-image scenarios spanning multiple platforms and materials, but it does not define clear trigger boundaries or exclusions. In a manifest file, this breadth can make invocation conditions ambiguous and increase unintended activation for ordinary image-design requests.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The skill text predominantly requires Chinese-language usage and examples, yet it is described for platforms like TikTok Live and Amazon Live that may involve users in other locales. Because no opt-in or language-selection guidance is provided, this can impose a specific language/locale on users without explicit choice.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The file presents itself as a generic AI utility supporting chat, image, video, model enumeration, uploads, and task polling, while the declared skill is narrowly scoped to GPT Image 2 livestream-commerce image generation. This scope mismatch increases the attack surface and can mislead reviewers or orchestrators into granting a narrowly intended skill far broader capabilities than expected.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: This Python skill’s docstring and CLI-facing help/messages are written in Chinese, establishing a fixed language/locale experience without any opt-in or alternative. The policy requires flagging language or locale constraints when the skill forces a specific language without user choice, and no multilingual option or justification is present in the file.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: Exposing text chat in an image-generation skill violates least privilege and enables arbitrary prompt forwarding to a text model unrelated to the skill's stated purpose. In an agent environment, that broadens what the skill can do beyond user expectations and may be abused for unintended data handling or policy bypass via an overly capable auxiliary interface.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This markdown file contains user-facing natural language almost exclusively in Chinese, which can constitute a language/locale policy issue when no opt-in or justification is provided. The file does not state that the skill is region-specific or that Chinese is an intentional locale constraint.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The example API key value uses Chinese text ('请替换为你的APIKey') as an instruction embedded directly in the configuration. This imposes a specific language in user-facing content without any indication that language selection is optional or region-specific.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Low

Category: Not specified by scanner
Confidence: 87% confidence
Finding: User-info and model-enumeration endpoints are outside the stated purpose of generating livestream images and reveal account metadata and available backend capabilities. While lower severity than chat/video exposure, they still expand reconnaissance value and break the principle of minimal disclosure for a narrowly scoped skill.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.