Back to skill

Security audit

桌面俯拍商品演示视频|AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly aligned with AI-HIVE video generation, but it needs Review because its API key can be sent to a user-configured API endpoint.

Install only if you trust AI-HIVE and are comfortable storing an API key locally. Do not use --base-url, AI_HIVE_BASE_URL, or config.json values from anyone else, and rotate the API key if it may have been used with an untrusted endpoint. Expect uploads of selected media and possible billable generation after confirmation.

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

Error
Location
scripts/videogen.py:91
Finding

Bearer Credential Disclosure Through an Unrestricted API Base URL

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Note
Location
scripts/videogen.py:7
Finding

Unpinned Runtime Dependency Installation

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
  • 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 (15)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The finding suggests the skill presents itself as a narrowly focused demo-video generator but also includes broader capabilities such as generic chat/image generation, account or wallet access, model inventory access, and local credential setup. When a skill has materially broader access than declared, it increases the risk of credential exposure, overcollection of user data, unintended account actions, and policy bypass through a misleadingly narrow description.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The finding suggests the skill presents itself as a narrowly focused demo-video generator but also includes broader capabilities such as generic chat/image generation, account or wallet access, model inventory access, and local credential setup. When a skill has materially broader access than declared, it increases the risk of credential exposure, overcollection of user data, unintended account actions, and policy bypass through a misleadingly narrow description.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
91% confidence
Finding

The finding suggests the skill presents itself as a narrowly focused demo-video generator but also includes broader capabilities such as generic chat/image generation, account or wallet access, model inventory access, and local credential setup. When a skill has materially broader access than declared, it increases the risk of credential exposure, overcollection of user data, unintended account actions, and policy bypass through a misleadingly narrow description.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill advertises executable workflows and includes shell commands, network access, file operations, and environment variable handling, but it does not declare any tool scope such as permissions or allowed-tools. In an agent environment, this weakens least-privilege boundaries and can lead to unintended execution of filesystem, shell, or network actions beyond what reviewers or orchestrators expect.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The invocation description and surrounding user-facing content are written entirely in Chinese and position the skill for Chinese-language requests, but there is no explicit opt-in or statement that other languages are supported. Under the policy for natural-language constraints, forcing a specific language without user choice can be a locale/language policy violation.

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 explicitly says to turn the request into a production-ready Chinese workflow, which imposes a language requirement regardless of user preference. This is a language/locale policy concern because the file does not offer a language choice or document a justified region-specific constraint.

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 file presents itself as a specialized tabletop product demo video skill, but actually embeds a broad, reusable AI Hive client supporting chat, image, video, model enumeration, uploads, and task polling. This capability mismatch increases attack surface and violates least privilege: a caller or wrapper expecting a constrained video skill could unintentionally gain access to unrelated AI operations and broader data handling paths.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The module documentation explicitly describes a general AI capability tool, which contradicts the claimed specialized skill identity. This kind of deceptive or misleading packaging is dangerous because reviewers, orchestrators, or users may grant permissions based on the narrower description while the code actually supports far broader operations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This code file contains natural-language user-facing descriptions that default to Chinese, including the module docstring and later CLI help text. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

Across the script, user-visible errors, prompts, argparse help strings, and progress messages are presented in Chinese only. Because the skill does not offer a language/locale choice or justify a Chinese-only scope, this violates the language/locale policy for natural-language content in code files.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Arbitrary text chat support is unjustified in a narrowly scoped tabletop product demo video skill and enables unrestricted prompting against external models. In skill ecosystems, this can be abused to bypass higher-level policy constraints, process unrelated sensitive text, or turn a specialized media tool into a general-purpose LLM proxy.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

Standalone image generation is broader than the declared purpose of a tabletop product demo video skill and unnecessarily widens model access and output capabilities. This makes the skill a multipurpose content-generation gateway rather than a constrained video workflow, increasing misuse potential and policy bypass risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The file’s natural-language description and CLI description are entirely in Chinese, and there is no indication that the user can choose another language or that the skill is intentionally restricted to a Chinese-speaking context. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

Exposing user-info and wallet balance lookup is unrelated to generating tabletop product demo videos and creates unnecessary access to account metadata. While not direct code execution, it expands sensitive surface area and can leak billing or account details to contexts that only needed media generation.

Content

No source excerpt is available for this finding.