Security audit

interactive-explainer

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed workflow for making educational explainer videos, with user approval gates before paid generation steps.

Before installing, review the Pruna skill sources you are adding with npx and confirm you are comfortable sending uploaded reference media, generated stills, audio, and prompts to the configured generation providers. Treat the approval gates as important cost and quality controls.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (16)

Rp1

Medium

Category: MCP Rug Pull
Confidence: 94% confidence
Finding: The skill instructs users to run `npx skills add ...` without pinning the package manager/tooling version, which introduces supply-chain risk because the fetched executable behavior can change over time or be replaced upstream. In a skill file, these commands are likely to be copied verbatim by users or agents, making the exposure operational rather than merely theoretical.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 94% confidence
Finding: The skill instructs users to run `npx skills add ...` without pinning the package manager/tooling version, which introduces supply-chain risk because the fetched executable behavior can change over time or be replaced upstream. In a skill file, these commands are likely to be copied verbatim by users or agents, making the exposure operational rather than merely theoretical.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 94% confidence
Finding: The skill instructs users to run `npx skills add ...` without pinning the package manager/tooling version, which introduces supply-chain risk because the fetched executable behavior can change over time or be replaced upstream. In a skill file, these commands are likely to be copied verbatim by users or agents, making the exposure operational rather than merely theoretical.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 94% confidence
Finding: The skill instructs users to run `npx skills add ...` without pinning the package manager/tooling version, which introduces supply-chain risk because the fetched executable behavior can change over time or be replaced upstream. In a skill file, these commands are likely to be copied verbatim by users or agents, making the exposure operational rather than merely theoretical.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 94% confidence
Finding: The skill instructs users to run `npx skills add ...` without pinning the package manager/tooling version, which introduces supply-chain risk because the fetched executable behavior can change over time or be replaced upstream. In a skill file, these commands are likely to be copied verbatim by users or agents, making the exposure operational rather than merely theoretical.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 94% confidence
Finding: The skill instructs users to run `npx skills add ...` without pinning the package manager/tooling version, which introduces supply-chain risk because the fetched executable behavior can change over time or be replaced upstream. In a skill file, these commands are likely to be copied verbatim by users or agents, making the exposure operational rather than merely theoretical.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 94% confidence
Finding: The skill instructs users to run `npx skills add ...` without pinning the package manager/tooling version, which introduces supply-chain risk because the fetched executable behavior can change over time or be replaced upstream. In a skill file, these commands are likely to be copied verbatim by users or agents, making the exposure operational rather than merely theoretical.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 94% confidence
Finding: The skill instructs users to run `npx skills add ...` without pinning the package manager/tooling version, which introduces supply-chain risk because the fetched executable behavior can change over time or be replaced upstream. In a skill file, these commands are likely to be copied verbatim by users or agents, making the exposure operational rather than merely theoretical.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 94% confidence
Finding: The skill instructs users to run `npx skills add ...` without pinning the package manager/tooling version, which introduces supply-chain risk because the fetched executable behavior can change over time or be replaced upstream. In a skill file, these commands are likely to be copied verbatim by users or agents, making the exposure operational rather than merely theoretical.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 94% confidence
Finding: The skill instructs users to run `npx skills add ...` without pinning the package manager/tooling version, which introduces supply-chain risk because the fetched executable behavior can change over time or be replaced upstream. In a skill file, these commands are likely to be copied verbatim by users or agents, making the exposure operational rather than merely theoretical.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 94% confidence
Finding: The skill instructs users to run `npx skills add ...` without pinning the package manager/tooling version, which introduces supply-chain risk because the fetched executable behavior can change over time or be replaced upstream. In a skill file, these commands are likely to be copied verbatim by users or agents, making the exposure operational rather than merely theoretical.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 94% confidence
Finding: The skill instructs users to run `npx skills add ...` without pinning the package manager/tooling version, which introduces supply-chain risk because the fetched executable behavior can change over time or be replaced upstream. In a skill file, these commands are likely to be copied verbatim by users or agents, making the exposure operational rather than merely theoretical.

Natural-Language Policy Violations

Medium

Confidence: 94% confidence
Finding: The instructions require `persona_gender` to be `female` or `male` and state that the selected voice must match that gender. This imposes a binary gender constraint in natural-language guidance without offering user choice, exceptions, or a documented policy reason.

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: The workflow text says `persona_gender` must be paired with a matching character descriptor and selects voices from gendered options, again enforcing a binary gender policy. This is a natural-language policy issue because it removes user choice and excludes other gender representations without justification.

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: The cast ledger example hard-codes `voice_language` to `English (US)`, which is a natural-language locale requirement. The file does not indicate this is optional, user-selectable, or limited to a justified region-specific use case, so it can violate language/locale choice policy.

Natural-Language Policy Violations

Low

Confidence: 95% confidence
Finding: This JSON template includes a natural-language locale constraint in the `voice_language` field: `English (US)`. The file does not indicate that users can opt into another language or that the English-only setting is required for a region-specific purpose, which fits the language/locale policy violation category.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.