Bilibili Data Provider

Security checks across malware telemetry and agentic risk

Overview

This appears to be a purpose-aligned Bilibili public-data skill, with the main caveat that it should more clearly disclose that user inputs are sent to Bilibili APIs.

Install this if you are comfortable with the agent sending Bilibili search terms, video IDs, or account identifiers to Bilibili's public APIs. Avoid entering private or sensitive identifiers unless necessary, and prefer a future version that documents exactly what data is transmitted and when.

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 (1)

Missing User Warnings

Low

Confidence: 90% confidence
Finding: The skill clearly depends on outbound network access to Bilibili public API endpoints, but the user-facing description around the tool section does not explicitly warn that prompts and parameters may be transmitted to an external service. This creates a transparency and privacy risk because users may provide search terms, video IDs, or account identifiers without realizing the action leaves the local agent environment.

VirusTotal

61/61 vendors flagged this plugin as clean.

View on VirusTotal