tierlist-video-maker

• Outcome: Review
• Latest audit: Jul 25, 2026 · 3:33 PM UTC
• Version: 0.1.0

Overview

The skill is coherent and video-focused, but it automatically installs online dependencies during normal use, so it should be reviewed before installation.

Install only if you are comfortable running this in an isolated Python environment where it may download packages, install Chromium, contact TierVibe/CDN resources, and use Microsoft online TTS. Prefer reviewing or preinstalling pinned dependencies yourself before running the scripts. The skill does not show evidence of credential use or hidden data exfiltration, but its automatic setup behavior changes the local environment.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Behavioral AST: exec() Call, eval() Call, Dynamic Import
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (9)

subprocess module call

Medium

• Category: Dangerous Code Execution

Content

except ImportError:
        import subprocess
        print("Installing playwright...", file=sys.stderr)
        subprocess.check_call([sys.executable, "-m", "pip", "install", "playwright", "-q"])
    import subprocess
    result = subprocess.run(
        [sys.executable, "-m", "playwright", "install", "chromium"],

• Confidence: 80% confidence
• Finding: subprocess.check_call([sys.executable, "-m", "pip", "install", "playwright", "-q"])

subprocess module call

Medium

• Category: Dangerous Code Execution

Content

if missing:
        import subprocess
        print(f"Installing: {', '.join(missing)}...", file=sys.stderr)
        subprocess.check_call([sys.executable, "-m", "pip", "install", *missing, "-q"])


ensure_deps()

• Confidence: 95% confidence
• Finding: subprocess.check_call([sys.executable, "-m", "pip", "install", *missing, "-q"])

subprocess module call

Medium

• Category: Dangerous Code Execution

Content

except ImportError:
        print("Installing edge-tts...", file=sys.stderr)
        import subprocess
        subprocess.check_call([sys.executable, "-m", "pip", "install", "edge-tts", "-q"])
        import edge_tts

    with open(script_path, "r", encoding="utf-8") as f:

• Confidence: 94% confidence
• Finding: subprocess.check_call([sys.executable, "-m", "pip", "install", "edge-tts", "-q"])

subprocess module call

Medium

• Category: Dangerous Code Execution

Content

import edge_tts
    except ImportError:
        import subprocess
        subprocess.check_call([sys.executable, "-m", "pip", "install", "edge-tts", "-q"])
        import edge_tts

    async def _list():

• Confidence: 92% confidence
• Finding: subprocess.check_call([sys.executable, "-m", "pip", "install", "edge-tts", "-q"])

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 93% confidence
• Finding: The skill clearly instructs the agent to use shell commands, read and write local files, and access the network, yet no permissions are explicitly declared. This creates a transparency and sandboxing gap: a host may expose broader capabilities than users or reviewers expect, increasing the risk of unintended file access, network exfiltration, or command execution if the skill or its dependencies are abused.

Context-Inappropriate Capability

Medium

• Confidence: 97% confidence
• Finding: Installing Python packages during execution expands the script's capability from media processing into environment modification. In a skill that may run on an agent host, this increases the attack surface by allowing unreviewed package resolution and installation at execution time, which can introduce malicious or compromised dependencies or destabilize the environment.

Context-Inappropriate Capability

Medium

• Confidence: 90% confidence
• Finding: Generating narration audio does not require the script to modify the Python environment at runtime, yet this code installs a package if absent. That broader capability increases supply-chain and environment-integrity risk, especially in an agent/automation context where operators may not expect dependency installation as a side effect.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The script performs automatic pip installation after only printing a brief message, with no opt-in or confirmation from the user. That behavior is risky because an operator may expect video generation only, while the script silently performs package management actions that can pull code from external sources and alter the execution environment.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The list_voices() path performs automatic pip installation without a clear up-front warning, so a user invoking a simple discovery command can trigger subprocess execution and external network access unexpectedly. In automation environments, this can violate change-control expectations and expose the host to supply-chain risk.

VirusTotal

65/65 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.