Back to skill

Security audit

无缝循环短视频生成器|AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

The skill is broadly aligned with AI-HIVE video generation, but it needs review because its API client can send a stored bearer key to an arbitrary configured endpoint.

Install only after reviewing the API endpoint and credential handling. Use the default AI-HIVE endpoint, remove any unexpected AI_HIVE_BASE_URL or ~/.ai-hive/config.json base_url value, avoid uploading sensitive media unless you trust the service, and expect authenticated generation calls may incur charges.

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 (2)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/videogen.py:91
Finding

Bearer API Credential Can Be Forwarded to an Arbitrary Server

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Note
Location
scripts/videogen.py:7
Finding

Unpinned Runtime Dependency Installation Guidance

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • 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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (13)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The skill presents itself as a seamless loop video generator with continuity checks and start/end state design, yet the available behavior appears limited to generic editing/utilities rather than the claimed workflow. Such overclaiming can cause operators to invoke the skill in contexts involving copyrighted assets, paid generation, or publication workflows under false assumptions about validation, authenticity checks, and loop-quality controls.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The skill presents itself as a seamless loop video generator with continuity checks and start/end state design, yet the available behavior appears limited to generic editing/utilities rather than the claimed workflow. Such overclaiming can cause operators to invoke the skill in contexts involving copyrighted assets, paid generation, or publication workflows under false assumptions about validation, authenticity checks, and loop-quality controls.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding

The skill advertises and demonstrates commands that can use environment variables, local files, networking, and shell execution, but it does not declare any explicit tool scope or permission boundaries. In an agent environment, this increases the chance that the skill is granted broader capabilities than intended, enabling network calls, filesystem access, or command execution without clear governance or review.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger phrase includes a broad term related to generic visual effects, which can cause the skill to activate outside its intended niche. Over-broad triggering is risky because it may route unrelated user requests into a skill that can suggest shell/network/file-based workflows and potentially initiate costly or inappropriate media-generation steps.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The natural-language string explicitly says to turn requests into a "production-ready Chinese workflow," which imposes a specific language choice by default. This is a locale/language policy issue because the file does not indicate that the user can choose another language or opt in to Chinese output.

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
98% confidence
Finding

The file is marketed as a seamless loop video generator, but the implementation is a broad AI-Hive client exposing unrelated capabilities such as text chat, image generation, model enumeration, user-info access, and arbitrary media upload. This creates unnecessary privilege and scope expansion, increasing the chance that an agent or user can invoke actions outside the declared skill purpose and leak information or spend account resources unexpectedly.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The module docstring and parser description explicitly frame the program as a generic AI capability caller, contradicting the loop-video-specific identity in the skill metadata. This kind of capability/identity mismatch is dangerous because reviewers, users, and orchestrators may grant trust based on the narrow manifest while the code exposes a much broader operational surface.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code file contains user-facing descriptions, prompts, errors, and CLI help primarily in Chinese, starting from the module docstring and continuing throughout the skill. Because the skill does not offer a language choice or document that it is intentionally region-specific, it creates a locale policy issue for users who did not opt into Chinese-only interaction.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The user-info endpoint exposes account information and wallet balance, which is unrelated to generating seamless loop videos. In an agent setting, this broadens data access beyond user expectations and can reveal sensitive billing or account metadata if the skill is invoked for a simple media task.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The general-purpose text chat function is unrelated to the skill's declared loop-video generation purpose and materially expands what the skill can do. This hidden capability can be abused to send arbitrary prompts and consume API credits or interact with models in ways the user did not request.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

Standalone image generation is outside the stated loop-video-specific contract and gives the skill extra generative power not justified by its manifest. In a tool-using agent environment, this mismatch undermines least privilege and can lead to unapproved content generation and unnecessary account spend.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The module docstring and argparse description present the skill name only in Chinese, which creates a language-specific experience without any visible user opt-in or alternative locale support. Under the policy rule for natural-language violations, this is a locale/language constraint that is not documented as optional or region-specific.

Content

No source excerpt is available for this finding.