Back to skill

Security audit

GEO AEO 内容增长中心|AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

This skill is mostly a disclosed AI-HIVE content workflow, but it handles API credentials and exposes configurable authenticated requests in ways users should review before installing.

Install only if you intend to use AI-HIVE and are comfortable storing an API key locally. Avoid setting custom AI_HIVE_BASE_URL or --base-url unless you fully trust the endpoint, review generated commands before running them, and confirm cost-bearing generation parameters before submitting jobs.

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 (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/imagegen.py:91
Finding

API Credential Disclosure Through an Unrestricted Base URL

Content
View full analysis
Remediation
View remediation
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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The declared purpose is strategic GEO/AEO content planning, but the described behavior includes broader model operations, asset generation, account/resource access, and potentially wallet/user-info queries that are not clearly disclosed in the top-level contract. This mismatch can mislead users and reviewers about what the skill is actually capable of, enabling unexpected data access, spending, or external operations under a benign-seeming label.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill advertises executable workflows involving environment variables, local file access, shell commands, and network calls, but it does not declare any explicit tool scope or permission boundaries. In an agent environment, this increases the risk of over-privileged execution, unintended external requests, local file exposure, or command execution beyond what the user expects.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

Standalone trigger keywords such as broad GEO/AEO-related terms can cause the skill to activate in contexts where the user did not intend to invoke a networked or execution-capable workflow. Overbroad auto-activation increases the chance of unnecessary exposure of user data, confusion, or accidental progression toward billable actions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The adaptation/use condition is broad enough to cover generic requests to turn reference material into original content, scripts, prompts, code, or task lists without sufficiently tight scope boundaries. In practice, this can pull the skill into adjacent areas like content imitation, copyright-sensitive transformation, or tool-assisted generation beyond the stated GEO/AEO planning role.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The default prompt hard-codes Chinese output ('production-ready Chinese workflow') regardless of user preference, which can override user intent and reduce transparency about what the system will produce. While not directly enabling code execution or privilege abuse, it can degrade safety and usability by causing unexpected outputs, especially when paired with automatic skill selection.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill enables implicit invocation while providing only a broad marketing-oriented description, which increases the chance the agent will auto-select this skill outside a narrowly intended context. Because the skill is designed to generate workflows, runnable commands, and content artifacts, unintended invocation could cause the system to produce operational guidance or API-facing actions without clear user intent verification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The file’s natural-language description and CLI description are hardcoded in Chinese branding/text without offering any language or locale choice. The policy allows locale constraints only when they are opt-in or clearly justified as region-specific, which is not stated here.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest describes a narrowly purposed skill for GEO/AEO content-growth support, with image-material generation as an implementation detail via AI-HIVE. However, this file implements a general-purpose AI Hive CLI covering user account info, wallet balance, model enumeration, text chat, standalone media upload, and video generation, which is materially broader than the declared skill purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This code file contains the primary skill description and nearly all user-facing prompts exclusively in Chinese, including the module docstring and CLI help text. Under the policy rule, forcing a specific language without user opt-in is a natural-language locale violation, and the file does not provide any option to select another language or explain a region-specific requirement.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

For a skill whose stated purpose is producing GEO/AEO content assets through AI-HIVE, interactive browser launching to account pages and querying user-info/wallet data are ancillary platform-management capabilities rather than task-specific content functions. These capabilities are not described in the manifest and are not obviously necessary to the end-user intent of GEO/AEO content production.

Content

No source excerpt is available for this finding.