Security audit

YouTube API

Security checks across malware telemetry and agentic risk

Overview

This is a coherent YouTube data lookup skill, but its JustOneAPI token is sent in URL query parameters, which users should treat as a credential-handling risk.

Install only if you trust JustOneAPI with your YouTube lookup requests and API token. Use a low-scope or easily rotated token, avoid exposing command lines or request URLs in logs/screenshots, and rotate the token if you think URLs or process arguments may have been captured.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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 (5)

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: The skill appends the API token as a query parameter, which exposes the credential in URLs. Query strings are commonly logged by proxies, servers, browser history, process listings, telemetry, and error messages, so the token can be leaked even when HTTPS is used. In this skill, the token is required for every request and there is no warning or mitigation, which makes accidental credential disclosure more likely.

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: The skill requires an access token to be sent as a query parameter, which is an insecure credential transport pattern. Query strings are commonly logged by clients, proxies, observability systems, browser history, and server infrastructure, increasing the chance of credential leakage even when HTTPS is used.

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: This second endpoint repeats the same insecure pattern by transmitting the API access token in the URL query string. Reuse across multiple operations expands exposure surface and makes accidental leakage through logs, traces, analytics tools, or copied URLs more likely.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: This operation requires an access token in a query parameter, but the documentation gives no warning that the credential is sensitive or that query strings are commonly exposed in logs, browser history, proxies, and monitoring systems. Even though this is documentation rather than executable code, it normalizes an unsafe authentication pattern and increases the chance that users will transmit or store secrets insecurely.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The second endpoint repeats the same issue: it requires a sensitive access token in the query string without any user-facing warning about credential handling risks. This can lead integrators to paste secrets directly into URLs, which may then be leaked through request logs, analytics tooling, referrer propagation, or shared debugging artifacts.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.