Back to skill

Security audit

AI大模型专家|小红书 电商图片生成与编辑

Security checks for vulnerabilities and agentic risk

Overview

The skill is purpose-aligned for AI-HIVE image generation, but it needs Review because its API key can be sent to an unvalidated custom server configuration.

Review this skill before installing. Use it only for intended AI-HIVE workflows, avoid setting --base-url or AI_HIVE_BASE_URL unless the endpoint is trusted, keep the API key scoped and revocable, and confirm before uploading private product media or submitting billable generation jobs. Prefer installing dependencies in a virtual environment with pinned versions.

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)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/imagegen.py:92
Finding

Bearer API Key Can Be Transmitted to an Arbitrary Endpoint

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Note
Location
SKILL.md:213
Finding

Unpinned Third-Party Dependency Installation

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 (7)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill documents and exposes capabilities that imply environment access, file read/write, network communication, and shell execution, but it does not declare any explicit tool scope or permission boundaries. In an agent ecosystem, this can lead to over-privileged execution, making it easier for prompt injection, unsafe parameter use, or unintended file/network actions to occur without policy enforcement.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger description is overly broad and includes many generic search and migration terms, which increases the chance the skill is invoked outside its intended scope. In an agent setting, overbroad routing can cause accidental data disclosure to external services, unintended API usage, or execution of file/network actions for queries that did not actually require this skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The original search-intent section names many competing tools, platforms, and broad commercial scenarios without clear triggering constraints, which encourages false-positive activation. Because this skill can upload media, use API credentials, poll remote tasks, and download outputs, accidental invocation expands the attack surface and may transmit user data to the vendor platform unnecessarily.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill enables implicit invocation but provides no visible trigger constraints, confirmation requirements, or scope limits in this file. Because the skill can submit jobs to an external AI-HIVE service, automatically save task IDs, poll status, and download results, an agent may invoke it unexpectedly from broad user intent, causing unintended external actions, cost incurrence, or data transfer.

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 subsequent CLI/help text are entirely in Chinese, and the skill title/description are also Chinese-facing. For a general-purpose image generation skill, this imposes a specific language/locale on users without any opt-in or documented regional justification, which matches the language-policy violation criterion.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

L006 在元数据中将语言固定为 zh-CN,但文档中未提供语言选择、用户 opt-in,或对该语言限制作出必要说明。按照语言/locale 政策,强制特定语言而无选择机制可能构成自然语言策略违规。

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

Earlier sections repeatedly describe this skill as supporting both text-to-image and optional reference-guided generation, including parameter docs marking --image as optional and examples without images. The FAQ answer at L340 says the capability requires a reference image, which directly conflicts with the documented behavior and could mislead users about the skill's actual intent and usage.

Content

No source excerpt is available for this finding.