Security audit

Вконтакте - публикация постов, фото и видео. Диалоги с посетителями. NodeJS

Security checks across malware telemetry and agentic risk

Overview

This VK community-management skill appears legitimate, but it asks users to grant broad, long-lived VK account access without enough safety controls or warnings.

Install only if you are comfortable allowing an agent to manage VK posts, uploads, and messages. Prefer the narrowest VK token that works, avoid offline full-rights user tokens when possible, do not put tokens in shared terminals or logs, set time limits for polling, leave auto-mark-as-read off unless intentional, and manually approve public posts, message actions, deletions, and raw VK API calls.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (7)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 91% confidence
Finding: The skill documentation describes network-capable operations against the VK API, but the skill metadata does not declare any corresponding permissions. This creates a transparency and governance gap: users and platform controls cannot accurately assess what the skill is allowed to do, which increases the risk of unintended outbound access and misuse.

Description-Behavior Mismatch

Medium

Confidence: 91% confidence
Finding: The guide explicitly tells users to fall back to arbitrary `fetch` or `curl` calls against any VK API method when the CLI lacks support, which broadens the skill from scoped community management into effectively unrestricted API operation. In the context of an agent skill, this creates capability expansion beyond the declared purpose and can enable actions the surrounding controls or reviewers did not intend to authorize.

Description-Behavior Mismatch

Medium

Confidence: 95% confidence
Finding: The reference recommends using a full-privilege user token with administrator capabilities and emphasizes that it can edit or delete any posts and upload content broadly. That materially exceeds a least-privilege design and increases the blast radius if the token is misused, exposed, or the skill behaves unexpectedly.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The documentation encourages use of a permanent VK User Token with broad permissions, including capabilities that can affect account and community state, but does not warn about token sensitivity, storage, rotation, or blast radius. A leaked or mishandled token could let an attacker post content, read messages, or delete posts, causing account compromise and community takeover effects.

Missing User Warnings

Medium

Confidence: 98% confidence
Finding: The CLI examples pass the access token directly as a positional command-line argument, which can leak secrets via shell history, process listings, logs, and job control output. Because the token grants API access, disclosure can immediately lead to unauthorized posting, message access, or account/community control depending on scope.

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: The guide recommends a non-expiring (`offline`) user token with broad administrator-like permissions without discussing the security tradeoff. A long-lived high-privilege credential greatly increases persistence and impact for any compromise, making token theft far more damaging than a short-lived or scoped credential.

Credential Access

High

Category: Privilege Escalation
Content: This skill allows you to manage a VK community using the VK API. ## Requirements - VK Access Token. **Важно:** Используйте **User Token** для полных прав (удаление постов, простая загрузка фото). См. [references/api.md](references/api.md) для деталей. - Node.js environment. ## Core Workflows
Confidence: 90% confidence
Finding: Access Token

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.