Back to skill

Security audit

爆款视频原创复刻工作台|AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a disclosed AI-HIVE video-generation workflow, but it has a real API-key handling risk that users should review before installing.

Install only if you trust the AI-HIVE workflow and are comfortable storing an API key locally. Do not set AI_HIVE_BASE_URL or --base-url to anything except the intended AI-HIVE HTTPS endpoint, and rotate the API key if it may have been used with an untrusted endpoint.

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:91
Finding

Arbitrary API Base URL Can Expose the AI-HIVE Bearer Credential

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (12)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

This mismatch is more security-relevant because it includes undeclared behaviors such as account/wallet retrieval, model enumeration, browser-based API key setup, and local credential storage. Undeclared credential handling and account-data access expand the attack surface and can lead users to expose secrets or authorize actions they did not reasonably expect from the skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

This mismatch is more security-relevant because it includes undeclared behaviors such as account/wallet retrieval, model enumeration, browser-based API key setup, and local credential storage. Undeclared credential handling and account-data access expand the attack surface and can lead users to expose secrets or authorize actions they did not reasonably expect from the skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

This mismatch is more security-relevant because it includes undeclared behaviors such as account/wallet retrieval, model enumeration, browser-based API key setup, and local credential storage. Undeclared credential handling and account-data access expand the attack surface and can lead users to expose secrets or authorize actions they did not reasonably expect from the skill.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill advertises code-driven operations involving environment variables, local files, networking, and shell commands, but it declares no explicit tool scope or permission boundaries. In an agent environment, this increases the chance that the skill can trigger broader-than-expected file/system/network actions without clear operator review, especially because it also references API keys, local paths, ffmpeg, and remote API usage.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The natural-language instruction in the default prompt says to produce a "production-ready Chinese workflow," which imposes a specific language choice by default. This is a language/locale policy issue because the file does not offer the user an explicit choice or opt-in for Chinese output.

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 hard-codes Chinese-language skill descriptions, CLI metadata, and search aliases such as '爆款视频原创复刻工作台|AI-HIVE' and related Chinese trigger terms. There is no indication that users can choose another language or that this locale restriction is documented as an explicit region-specific requirement, which makes this a natural-language policy concern.

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
96% confidence
Finding

The module docstring states it wraps text chat, image generation, video generation, model queries, media upload, and task polling as a general AI capability tool, and the code implements corresponding commands such as chat and image. The manifest describes a specialized skill for authorized viral-video original remake workflows centered on analysis, creative adaptation, generation, and delivery via AI-HIVE, not a broad general-purpose chat/image tool.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The module docstring presents the skill entirely in Chinese as the default interaction language, and the rest of the user-facing strings follow that same fixed locale. For a general-purpose skill, this constitutes a language/locale constraint that is not presented as optional or region-specific.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The get_user_info endpoint and the user-info CLI command retrieve user information and wallet balance, as reflected again in the parser help text. Account/balance inspection is ancillary platform administration functionality and is not part of the manifest’s described purpose of producing authorized original-remake video deliverables.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The generated SKILL_CONFIG hard-codes Chinese-language discovery and presentation metadata for the skill, which can force a specific language experience in activation and display. There is no indication that the user can choose another language or that this is a region-limited skill.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The code implements model listing and filtering, and exposes it through the models command. While internal model lookup for generation may be expected, a user-facing capability to enumerate the full platform model catalog is broader than the manifest’s narrowly described remake workstation behavior.

Content

No source excerpt is available for this finding.