Back to skill

Security audit

AI大模型专家|电商爆款带货视频生成与编辑

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches its AI-HIVE video-generation purpose, but it can send the user's API key to an arbitrary configured server and allows broad automatic invocation, so it needs review before installation.

Install only if you intend to use AI-HIVE for video generation and are comfortable with media uploads and possible API charges. Avoid setting --base-url, AI_HIVE_BASE_URL, or config base_url to anything except the official AI-HIVE endpoint, and review any automatic invocation before letting the agent upload files or start tasks.

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

Error
Location
scripts/videogen.py:71
Finding

Arbitrary API Base URL Can Receive AI-HIVE Bearer Credentials

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
96% confidence
Finding

The skill advertises operational behaviors that involve shell execution, network access, environment/config handling, and file writes, but it does not declare any explicit tool scope or least-privilege boundaries. In an agentic environment, this can allow the skill to be invoked with broader capabilities than users or platform policy expect, increasing the chance of unauthorized local file access, credential handling, or unintended external requests.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description contains very broad trigger language covering many generic AI, video, ecommerce, advertising, and migration intents, making it likely the skill will activate for loosely related requests. Over-broad routing can cause an agent to use this skill in contexts the user did not intend, which is risky here because the skill can upload files, use API keys, submit billable jobs, and write outputs.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The metadata explicitly sets the language to 'zh-CN', and the document is written as a Chinese-localized skill without offering any user choice or opt-in for language/locale. Under the policy, forcing a specific language or locale without documented justification or user selection is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The search-intent section enumerates an unusually wide set of platforms, tools, models, and commercial scenarios without clear boundaries, which can lead to accidental invocation from simple mentions of third-party products or ecommerce channels. In this skill's context, mistaken activation is more dangerous because it may initiate external API workflows and media handling rather than staying informational.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest allows implicit invocation with no trigger scope, user-confirmation boundary, or contextual constraints. Because this skill can upload user-provided media, submit jobs to an external AI-HIVE service, poll task status, and download outputs, automatic invocation increases the chance of unintended data transfer, unexpected external actions, and unapproved cost-incurring operations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The module docstring and user-facing guidance are written entirely in Chinese, and later prompts/errors continue that assumption. Because this is a general-purpose AI/video skill rather than an explicitly region-specific compliance tool, the file imposes a locale expectation without user opt-in or an alternative language path.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The example API key value includes Chinese text ('请替换为你的APIKey'), which imposes a specific language in user-facing configuration content. The file does not offer a language choice or explain why a Chinese-only locale is required, so this appears to violate the language/locale policy for natural-language content.

Content

No source excerpt is available for this finding.