ClawHub
Back to skill

Security audit

ReelOnce-skill

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent text-to-video automation skill, but using it means installing/running project dependencies and sending media-generation inputs to configured providers.

Install this only in a repository and virtual environment you trust, review the Python and npm dependency manifests before rendering, and avoid sensitive prompts, images, audio, or reference media unless the configured providers are approved for that data. Use no-render or no-upload style options when you want to limit rendering or provider transmission.

A.I.G

Vulnerability Patterns
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (7)

Lp1

High
Category
MCP Least Privilege
Confidence
82% confidence
Finding

The file has effective process-execution capability via subprocess.run, but the finding indicates that this capability is not declared in the skill's permissions model. In an agent/skill environment, undeclared execution capability is dangerous because it can bypass operator expectations and policy controls, especially in a skill that orchestrates a full media-generation pipeline and may process untrusted user input.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill documents that it will automatically execute npm install and rendering inside a generated project directory, but it does not prominently warn users that this causes local command execution, dependency installation, network access, and extensive filesystem writes. That creates supply-chain and host-integrity risk, especially because npm install may run package scripts and modify the environment beyond simple video generation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill clearly describes image/video generation workflows and references third-party video capabilities and API keys, but it does not explicitly warn users that their prompts, images, reference media, or derived outputs may be transmitted to external services. In a media-generation pipeline, that omission can cause users to unknowingly send sensitive content off-host, creating privacy, confidentiality, and compliance risks.

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/agent_api.py (reported line 24)May include surrounding context.

python
def _run_command(args: List[str]) -> Dict[str, Any]:
    result = subprocess.run(
        [sys.executable, str(RUN_SCRIPT), *args, "--json"],
        capture_output=True,
        text=True,

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The CLI sets --language to zh by default, which imposes a specific locale unless the caller explicitly overrides it. This is a natural-language policy concern because the skill defaults users into one language rather than offering a neutral default or requiring opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The entire skill description is written in Chinese and does not indicate that other languages are supported or that Chinese is required for a region-specific or compliance-related reason. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The script emits a user-facing installation error message entirely in Chinese, which imposes a specific language choice on all users. The file does not offer an alternative language or any user opt-in for locale selection.

Content

No source excerpt is available for this finding.