Security audit

广告图片

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed AI Hive ad-image generator; its main risks are normal API-key storage, user-selected image uploads, and an unpinned dependency install, not hidden or destructive behavior.

Before installing, use an isolated environment if possible, consider pinning `requests`, and only provide reference images and an AI Hive API key you are comfortable sending to AI Hive and its upload/download storage flow. Expect the init command to open a browser and store the API key locally in `~/.ai-hive/config.json`.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:58
Finding: Unpinned Runtime Dependency Installation
Content: View full analysis
Remediation: View remediation

SkillSpector

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
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration

Findings (4)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 89% confidence
Finding: The skill invokes a Python script with network, shell, file, and environment access but does not declare any explicit tool scope or permissions boundary. That mismatch can cause an agent runtime to grant broader capabilities than a reviewer or user expects, increasing the risk of unintended file access, secret exposure, or outbound requests if the script is modified or misused.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The manifest description and main instructions are written as mandatory Chinese-language guidance, while also embedding English trigger terms, but nowhere state that the skill is China-specific or that users may choose another language. This can violate language/locale policy because it effectively constrains interaction language without explicit opt-in or documented justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The module docstring and user-facing CLI guidance are written entirely in Chinese, and the skill does not provide any opt-in or fallback for other languages. This creates a natural-language policy concern because the skill implicitly forces a specific language/locale on all users.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: The skill’s stated purpose is generating testable ad images via AI Hive, but the init flow also launches a browser to a chat page and appends from=cli-skill&skill=... for backend attribution. Opening a browser for API key setup is understandable, but adding tracking-style attribution metadata is not necessary to the core ad-image function described in the manifest.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.