Back to skill

Security audit

汽车功能演示视频|AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

This automotive video skill is mostly coherent, but it needs review because its API client can send the user's AI-HIVE key to arbitrary configured endpoints and can download server-named files without enough validation.

Install only if you trust the publisher and the AI-HIVE endpoint you will use. Avoid custom base URLs unless you control them, keep API keys out of command history, review ~/.ai-hive/config.json before authenticated runs, and prefer --no-download or a disposable output directory when testing task downloads.

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 (3)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/videogen.py:91
Finding

API Credentials Can Be Transmitted to an Attacker-Controlled Endpoint

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
scripts/videogen.py:401
Finding

Server-Controlled Task Metadata Can Cause Arbitrary File Downloads and Path Traversal

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
scripts/videogen.py:7
Finding

Unpinned Third-Party Dependency Installation Creates Supply-Chain Risk

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (13)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The declared description promises a substantial automotive video-generation and delivery workflow, including intake of authorized source materials, generation of multiple creative outputs, and AI-HIVE API-based media production operations. The supplied code does none of that. It only parses command-line arguments and emits a deterministic draft JSON file with predefined fields. While this could be a supporting component for a larger skill, the provided chunk's actual behavior is materially narrower than the declared purpose and lacks the core advertised capabilities.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared description describes a specialized automotive marketing/demo content skill with AI-assisted asset generation and domain-specific outputs. The supplied code does not implement those behaviors. Instead, it is a generic ffmpeg wrapper for simple video manipulation tasks. While basic video editing could be a supporting component of a larger video-production skill, this code chunk alone materially differs from the declared primary purpose and omits the core advertised capabilities and integrations. There are no suspicious undeclared capabilities beyond generic file/media processing, but the description does not accurately represent what this code actually does.

Content

No source excerpt is available for this finding.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 81)May include surrounding context.

md
python3 scripts/videogen.py init --skill-name automotive-feature-demo-ai-hive

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 83)May include surrounding context.

md
python3 scripts/videogen.py init --skill-name automotive-feature-demo-ai-hive

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill advertises executable commands and API-driven workflows but declares no explicit tool scope or permission boundaries. In a skill ecosystem, this can cause the runtime or reviewer to underestimate that the skill may access environment variables, local files, shell commands, or the network, increasing the chance of unintended secret exposure or unsafe execution paths.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Overly broad trigger phrases can cause the skill to activate in unrelated car or product-content conversations, leading to inappropriate routing into workflows that may request files, invoke external services, or encourage paid generation actions. In this context, broad activation increases the attack surface for prompt confusion, accidental tool use, and unintended disclosure of business assets or media.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The natural-language instruction in the default prompt requires a "production-ready Chinese workflow," which imposes a specific language choice by default. The file does not offer the user a language option or document a justified region-specific constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

This code file includes user-facing natural-language strings entirely in Chinese, including the skill description, argparse description, skill name, and search aliases. The file does not offer any language choice or explain that the skill is intentionally region-specific, which can violate a language/locale policy requiring user opt-in or justification.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/edit_video.py (reported line 20)May include surrounding context.

python
def run(args: list[str]) -> None:
    print(" ".join(args))
    subprocess.run(args, check=True)


def main() -> None:

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file implements a broad, reusable AI Hive client with text chat, image generation, model listing, media upload, and generic task polling, while the declared skill is narrowly scoped to automotive feature demo video generation. This scope mismatch expands the capability surface available through the skill package and can enable unintended use outside the manifest’s restrictions, weakening policy boundaries and increasing abuse potential.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The module docstring and CLI/parser descriptions repeatedly present the tool as a ‘通用 AI 能力调用工具’ and advertise general AI capabilities, contradicting the automotive-only manifest. Misleading scope documentation matters because operators and higher-level agents may trust the manifest while the implementation encourages broader use, creating a policy-confusion channel that can be exploited to invoke out-of-scope functionality.

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 user-facing natural-language strings and the top-level docstring is entirely in Chinese, presenting the tool as a general-purpose interface without documenting a locale restriction or opt-in. Under the policy rule, forcing a specific language in user-facing instructions is a language/locale policy violation unless the skill offers choice or clearly justifies the constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The manifest description defines usage through Chinese-only trigger phrases and content descriptions, but does not indicate that other languages are supported or that the user can opt into this locale. Under the stated policy, a language-specific constraint should either be optional or clearly documented as a justified regional limitation.

Content

No source excerpt is available for this finding.