Back to skill

Security audit

avatar-single-scene

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed workflow for generating a single approved avatar video scene, with visible user gates before paid generation.

Before installing, review the visible npx install commands and consider pinning or otherwise verifying the skill sources. Use this only when you are comfortable uploading portrait/audio/script material to Pruna generation services and spending API credits after the approval gates.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (8)

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding
The skill instructs operators to run `npx skills add ...` without pinning the `skills` package/tooling to a specific version. Because `npx` resolves and executes packages dynamically, a future compromised or incompatible release in the execution chain could change behavior or execute attacker-controlled code during install/use.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding
The skill instructs operators to run `npx skills add ...` without pinning the `skills` package/tooling to a specific version. Because `npx` resolves and executes packages dynamically, a future compromised or incompatible release in the execution chain could change behavior or execute attacker-controlled code during install/use.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding
The skill instructs operators to run `npx skills add ...` without pinning the `skills` package/tooling to a specific version. Because `npx` resolves and executes packages dynamically, a future compromised or incompatible release in the execution chain could change behavior or execute attacker-controlled code during install/use.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding
The skill instructs operators to run `npx skills add ...` without pinning the `skills` package/tooling to a specific version. Because `npx` resolves and executes packages dynamically, a future compromised or incompatible release in the execution chain could change behavior or execute attacker-controlled code during install/use.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding
The skill instructs operators to run `npx skills add ...` without pinning the `skills` package/tooling to a specific version. Because `npx` resolves and executes packages dynamically, a future compromised or incompatible release in the execution chain could change behavior or execute attacker-controlled code during install/use.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding
The skill instructs operators to run `npx skills add ...` without pinning the `skills` package/tooling to a specific version. Because `npx` resolves and executes packages dynamically, a future compromised or incompatible release in the execution chain could change behavior or execute attacker-controlled code during install/use.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding
The skill instructs operators to run `npx skills add ...` without pinning the `skills` package/tooling to a specific version. Because `npx` resolves and executes packages dynamically, a future compromised or incompatible release in the execution chain could change behavior or execute attacker-controlled code during install/use.

Natural-Language Policy Violations

Medium
Confidence
78% confidence
Finding
The instructions require selecting a `voice_language`, but the skill does not state that the user may choose their preferred language or locale, nor does it justify a fixed locale restriction. Under the policy, language constraints should be opt-in or clearly documented as region-specific.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.