Security audit

HeyGen 视频生成替代｜AI 视频生成与编辑

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent AI video-generation helper, but it needs Review because it uploads local media and downloads files using weakly validated server-provided URLs and filenames.

Install only if you are comfortable sending selected images/videos and prompts to AI Hive and saving an API key locally. Prefer a virtual environment, avoid sensitive source media, use a controlled output directory, and review or patch URL validation and taskId filename handling before production use.

A.I.G

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

Warning

Location: scripts/heygen_visual.py:169
Finding: Unrestricted Server-Provided Media Transfer URLs
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/heygen_visual.py:272
Finding: Server-Controlled Task Identifier Used in a Local File Path
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Note

Location: SKILL.md:94
Finding: Unpinned Third-Party Dependency Installation
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 89% confidence
Finding: The skill invokes Python scripts, installs dependencies, uses local files, references environment-derived paths like $SKILL_PATH, and communicates with a remote API, but it does not declare any explicit tool or permission scope. This creates a trust gap: a host agent may expose shell, filesystem, environment, or network capabilities more broadly than intended, increasing the chance of unintended data access, command execution, or outbound requests if the skill is used in an automation context.
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 includes its primary docstring and CLI descriptions in Chinese, effectively forcing a specific language for user interaction. The policy allows locale constraints only when users are given a choice or the restriction is clearly justified, neither of which appears here.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.