Back to skill

Security audit

电商爆款文案生成器|AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for AI-HIVE ecommerce content generation, but it can send the user's AI-HIVE API key to an arbitrary configured endpoint.

Review this skill before installing. Use it only with AI-HIVE credentials you can rotate, avoid setting AI_HIVE_BASE_URL or --base-url unless you fully trust the endpoint, and confirm prompts, media uploads, routing, and costs before running generation commands.

Vulnerability Patterns
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (2)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/imagegen.py:91
Finding

AI-HIVE API Credential Can Be Forwarded to an Arbitrary Endpoint

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
scripts/videogen.py:91
Finding

AI-HIVE API Credential Can Be Forwarded to an Arbitrary Endpoint

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • 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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (16)

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The skill claims to be a '电商爆款文案生成器' but the observed behavior is primarily video/multimedia generation with broader OpenAPI functions such as media handling and account/model queries. In this context, the mismatch is especially risky because ecommerce workflows often involve brand assets, user-provided media, and paid generation tasks, so hidden or under-disclosed capabilities can cause privacy, cost, and compliance issues.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The skill claims to be a '电商爆款文案生成器' but the observed behavior is primarily video/multimedia generation with broader OpenAPI functions such as media handling and account/model queries. In this context, the mismatch is especially risky because ecommerce workflows often involve brand assets, user-provided media, and paid generation tasks, so hidden or under-disclosed capabilities can cause privacy, cost, and compliance issues.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The skill claims to be a '电商爆款文案生成器' but the observed behavior is primarily video/multimedia generation with broader OpenAPI functions such as media handling and account/model queries. In this context, the mismatch is especially risky because ecommerce workflows often involve brand assets, user-provided media, and paid generation tasks, so hidden or under-disclosed capabilities can cause privacy, cost, and compliance issues.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The file is presented as an ecommerce copywriting skill, but the implementation is a generic AI-Hive media client with chat, image, upload, and video-generation capabilities. This capability mismatch is dangerous because it expands what the skill can do beyond what operators and users would reasonably authorize, increasing the risk of hidden functionality, policy bypass, and misuse of API-backed media generation under a misleading label.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The embedded SKILL_CONFIG brands the tool as a copywriting generator, but the actual entrypoint routes to video generation and media upload workflows. In a plugin/agent ecosystem, this kind of deceptive packaging can cause unsafe tool invocation, accidental granting of broader permissions, and operator misunderstanding about what data is uploaded or what content is produced.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill advertises executable workflows and includes shell commands, environment-variable usage, file I/O, and networked API interactions, but declares no explicit tool scope or permissions boundary. That creates an authorization ambiguity where a host agent may over-grant capabilities or invoke the skill without clear least-privilege constraints, increasing the chance of unintended network calls, local file access, or secret exposure.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The activation criteria include broad phrases like transforming a reference case into original content and serving many marketing/media scenarios, which can cause the skill to trigger in contexts far beyond narrowly defined ecommerce copywriting. Over-broad triggering increases the chance of accidental invocation on sensitive or non-compliant requests, including copyright-adjacent imitation, disallowed marketing claims, or unnecessary exposure of media-generation capabilities.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The default prompt explicitly requires a "production-ready Chinese workflow," which imposes a specific language on users. This is a natural-language policy concern because the file does not indicate any user choice, opt-in, or documented justification for restricting output to Chinese.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

Enabling implicit invocation without narrowly defined trigger constraints can cause the skill to activate in response to loosely related requests, exposing users to unrequested workflow generation, code suggestions, or external API-oriented actions. In this skill’s context, that risk is elevated because it can produce runnable AI-HIVE commands and operational marketing outputs, increasing the chance of accidental execution paths or inappropriate use in sensitive commercial contexts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The file embeds Chinese-only natural-language identifiers in the module docstring, argument parser description, and skill name. This appears to impose a specific language/locale on users without any opt-in or justification that the tool is intended only for a Chinese-language or region-specific context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code file contains user-facing descriptions, help text, and operational instructions entirely in Chinese, beginning with the module docstring and continuing throughout the CLI. Under the policy for natural-language violations, forcing a specific language without opt-in is reportable when no alternative locale or language choice is offered.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The packaged skill claims to be a focused ecommerce copywriter/image-generation tool, but the code exposes broader account, model enumeration, chat, upload, and generic generation operations. That scope expansion violates least privilege and increases the attack surface: a caller expecting a narrow skill could leverage it to access wallet/user metadata, enumerate available models, and perform unintended API actions under the user's API key.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file contains full video-generation support even though the skill metadata describes an ecommerce copywriting/image-generation use case. Hidden or undocumented media-generation capabilities can be abused to spend credits, process additional user media, and bypass policy or product-level restrictions that rely on the skill being narrowly scoped.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The module and CLI explicitly describe a general-purpose AI capability tool, which conflicts with the declared identity of a narrowly scoped ecommerce copywriter skill. This inconsistency is dangerous because it undermines user consent and security review assumptions, making it easier for broad capabilities to hide behind a seemingly limited business purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code file contains natural-language descriptions and CLI guidance entirely in Chinese, starting with the module docstring and continuing through user-facing help text. Under the policy, forcing a specific language without offering a user choice is a natural-language policy violation unless the locale constraint is clearly documented and justified, which it is not here.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The top-level docstring explicitly presents this file as a '通用 AI 能力调用工具' wrapping chat, image, video, model query, upload, and polling. That documented intent conflicts with the manifest for a specialized ecommerce viral copywriter skill, indicating the file is repurposed generic tooling rather than purpose-aligned implementation.

Content

No source excerpt is available for this finding.