Back to skill

Security audit

房产样板间漫游视频|AI-HIVE

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches a real-estate video workflow, but it uses API keys and media uploads while allowing an arbitrary API endpoint that could receive credentials or files.

Review before installing. Use only the default AI-HIVE endpoint, avoid setting AI_HIVE_BASE_URL or --base-url unless you fully trust the destination, and do not upload private property media unless you are comfortable sending it to the configured service. Treat ~/.ai-hive/config.json as a stored secret and prefer an isolated Python environment with reviewed dependencies.

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

Arbitrary API endpoint override can disclose bearer credentials and uploaded media

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
scripts/videogen.py:7
Finding

Unpinned third-party dependency installation produces a non-reproducible supply chain

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • 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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (10)

Tp4

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

A specialized skill that actually exposes broader generic media, account, model-listing, and API-key setup capabilities than declared creates a dangerous trust boundary mismatch. Users may grant or invoke the skill expecting a narrow real-estate-video workflow, while the underlying capability set could access account metadata, broader uploads/downloads, or other operations outside the expected scope, increasing the risk of over-privileged use and unintended data exposure.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

A specialized skill that actually exposes broader generic media, account, model-listing, and API-key setup capabilities than declared creates a dangerous trust boundary mismatch. Users may grant or invoke the skill expecting a narrow real-estate-video workflow, while the underlying capability set could access account metadata, broader uploads/downloads, or other operations outside the expected scope, increasing the risk of over-privileged use and unintended data exposure.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

A specialized skill that actually exposes broader generic media, account, model-listing, and API-key setup capabilities than declared creates a dangerous trust boundary mismatch. Users may grant or invoke the skill expecting a narrow real-estate-video workflow, while the underlying capability set could access account metadata, broader uploads/downloads, or other operations outside the expected scope, increasing the risk of over-privileged use and unintended data exposure.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill advertises and includes executable command examples that rely on environment variables, filesystem access, network calls, and shell execution, but it declares no explicit tool scope or permission boundaries. In an agent environment, this increases the chance the agent invokes sensitive capabilities without clear confinement or user awareness, especially because the workflow includes API keys, uploads, downloads, and local file operations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest's default prompt instructs the skill to produce a "production-ready Chinese workflow," which imposes a specific language choice in natural-language behavior. There is no indication that the user can choose another language or explicitly opt into 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’s natural-language description and skill-identifying strings are entirely fixed to Chinese, including the docstring and argparse description, with no indication that users may choose another language or locale. This can violate language/locale policy when a skill implicitly forces a specific language rather than offering an opt-in or documenting a justified regional 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 exposes broad generic AI operations—text chat, image generation, video generation, model enumeration, task polling, and arbitrary media upload—despite being packaged as a specialized real-estate walkthrough video skill. This scope expansion weakens policy boundaries and makes it easier to repurpose the skill for unrelated or prohibited content generation, especially since the generic endpoints are still implemented and callable from the same module.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This Python file contains user-facing natural-language strings and documentation exclusively in Chinese, including setup instructions and CLI guidance. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation because the skill does not offer any locale or language selection.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The top-level documentation says this is a '通用 AI 能力调用工具' and lists text chat, image generation, video generation, model query, upload, and polling as first-class capabilities. But the embedded skill configuration and manifest package this file as a specialized房产样板间漫游视频 skill, so the documentation actively frames a materially different intent than the deployed skill claims.

Content

No source excerpt is available for this finding.