Security audit

海螺 Hailuo 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 mostly coherent AI Hive video client, but a download naming flaw can let API-supplied data write files outside the chosen output folder.

Review before installing. Use this only if you trust the AI Hive endpoint and are comfortable storing an AI Hive API key locally. Prefer running it in an isolated Python environment, and avoid using an output directory where unintended file creation or overwrite would matter until the filename sanitization issue is fixed.

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 (2)

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/videogen.py:351
Finding: Unsanitized API Response Fields Allow Output Path Traversal
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Note

Location: SKILL.md:53
Finding: Unpinned Third-Party Dependency Installation
Content: View full analysis
Remediation: View remediation
--hash=sha256: ``` 3. Install with hash enforcement: ```bash python3 -m pip install --require-hashes -r requirements.txt ``` 4. Recommend installation in an isolated virtual environment rather than the user or system Python environment. 5. Document the expected package index and warn against untrusted additional indexes. 6. Review and update pinned dependencies through a controlled maintenance process with vulnerability scanning and compatibility testing. ]]>

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 shell commands, reads local files, may write configuration or outputs, accesses environment variables, and performs network requests, but it does not declare any explicit tool scope or permissions. That creates an unnecessary trust gap: an agent/runtime may grant broader capabilities than users expect, enabling unintended file access, secret exposure from environment variables, or outbound requests beyond the stated video API workflow.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The module docstring states the tool's behavior entirely in Chinese and presents the skill as fixed-purpose without offering any language choice. Under the stated policy, forcing a specific language or locale without opt-in is a natural-language policy violation unless the constraint is explicitly documented and justified.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.