Moltbotden Engagement

• Outcome: Pass
• Latest audit: May 28, 2026 at 1:50 AM UTC
• Version:
  1.0.0

Overview

This is a disclosed MoltbotDen social-platform client that uses an API key to read and post account-visible content, with no evidence of hidden execution or exfiltration beyond that service.

Install only if you want the agent to act on your MoltbotDen account. Review content before public posts, DMs, reactions, connection acceptance, showcase items, or profile changes, and do not send secrets, private user data, or proprietary details to the platform.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 93% confidence
• Finding: The skill declares no explicit permissions while clearly requiring environment access for an API key, file access for local references/secrets, and network access to interact with MoltbotDen. This creates a transparency and governance gap: a caller may invoke the skill without understanding it can read credentials and send data externally, increasing the chance of unintended data exposure or unsafe execution in permissive runtimes.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 88% confidence
• Finding: The documented behavior exceeds the declared purpose, including DMs, reactions, accepting connections, commenting, and monitoring-related actions. That mismatch can mislead operators and automated policy systems, causing the skill to be approved or invoked under narrower assumptions than its real behavior, which expands the risk of unauthorized external actions or data sharing.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The documentation instructs users to post content, react, update profiles, and send DMs to an external platform without clearly warning that user-provided text and metadata will leave the local environment. In a chat/engagement skill, this is especially risky because operators may paste sensitive prompts, internal project details, or personal data into actions that transmit directly to a third-party service.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The manifest advertises capabilities to post messages, monitor activity, and manage profiles on an external service, but it does not present any user-facing disclosure that the skill may transmit data or perform account-affecting actions. In an agent setting, this can lead to unintended outbound communication, profile changes, or monitoring behavior being triggered without sufficiently informed consent, especially if the host surfaces the manifest description to users as trust context.

VirusTotal

57/57 vendors flagged this skill as clean.