Maxhub Twitter

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Twitter/X lookup skill that uses a disclosed MaxHub API key and network access, with privacy and accidental-trigger caveats but no evidence of hidden or destructive behavior.

Install only if you are comfortable sending Twitter/X lookup terms and identifiers to MaxHub. Use explicit Twitter/X prompts to avoid accidental external queries, keep MAXHUB_API_KEY secret, and avoid submitting confidential or sensitive investigation terms unless you trust MaxHub's handling of that data.

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 (5)

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The example triggers are extremely broad single-word phrases such as “推文”, “详情”, “用户”, “资料”, “搜索”, and “趋势”, which are common in normal conversation. In agent systems that infer skill invocation from natural language, this can cause accidental activation of the Twitter/X skill and unintended external data queries, especially because the skill exposes broad search and user-data retrieval functions.

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The routing rules use very broad trigger terms such as 'user', 'post', and 'reply', which can match ordinary conversation and send the agent down an unintended execution path. In a skill that autonomously performs API calls, ambiguous routing can cause unnecessary third-party queries, privacy-impacting data transmission, or actions based on misunderstood user intent.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The skill states that it uses the MaxHub API but does not clearly warn users that their requested queries, identifiers, and search terms will be sent to a third-party service. This creates a transparency and privacy risk because users may provide sensitive investigation targets, internal brand-monitoring terms, or personal data without understanding the external disclosure.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The document instructs users to send search keywords and authenticated requests to an external domain (`www.aconfig.cn`) but provides no warning that user queries and API credentials are being transmitted off-platform. In a Twitter/X data skill, search terms may contain sensitive investigative topics, personal data, or proprietary interests, so the lack of disclosure increases the risk of unintended data exposure and unsafe operator use.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The document instructs use of an Authorization bearer token against an external domain but provides no warning that using the skill will transmit authenticated requests and potentially sensitive query data to a third-party service. In an agent-skill context, this can cause users or orchestrators to unknowingly send secrets and user-derived data off-platform, increasing credential exposure and unintended data sharing risk.

VirusTotal

57/57 vendors flagged this skill as clean.

View on VirusTotal