Security audit

Analysis of comments on Bilibili videos

Security checks across malware telemetry and agentic risk

Overview

This Bilibili skill is coherent and disclosed, but it can use full Bilibili session cookies and may install dependencies or save fetched media/comment data locally.

Install only if you are comfortable with a Bilibili automation tool. Prefer a virtual environment, review dependencies before running setup helpers, avoid using your primary Bilibili session cookies, keep credential persistence off unless needed, and confirm any publish/edit/schedule action before allowing it to run.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Missing User Warnings

Medium

Confidence: 78% confidence
Finding: The skill processes user-generated comments and danmaku and exports them into a report, but the description does not prominently warn about collection, analysis, retention, and export of third-party content. This creates a privacy and compliance risk because users may trigger bulk collection and local storage without clear notice.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The script automatically installs missing Python packages without explicit user confirmation, which causes code from external package repositories to be fetched and executed in the user's environment. In an agent skill context this is more dangerous because users may run setup helpers with elevated trust, creating supply-chain and environment-modification risk without informed consent.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal