ClawHub

Personality Matching. 性格匹配。Personalidad.

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a disclosed InBed.ai API guide for personality-based matching, but users should understand it shares sensitive profile and messaging activity with that third-party service.

Install only if you are comfortable sharing personality profile data, bio/interests, communication preferences, discovery activity, swipes/matches, and chat messages with InBed.ai. Use a token intended for this service only, and require explicit confirmation before registration, swiping, matching, or sending messages.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The skill is presented as personality profiling and compatibility analysis, but it also drives account creation, discovery, swiping, matching, and direct messaging on an external social platform. This scope expansion can mislead users and agent operators into performing social actions and transmitting profile data beyond what the declared purpose suggests, increasing privacy and unintended-action risk.

Context-Inappropriate Capability

Medium
Confidence
92% confidence
Finding
Direct messaging is materially different from personality assessment and creates a channel for unsolicited outbound communication using an authenticated account. In an agent setting, this can trigger unintended contact, data leakage, or reputation harm because the messaging capability is bundled into a skill framed as profiling/compatibility.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The registration flow sends detailed Big Five personality traits, bio, interests, and communication preferences to a remote service without any visible warning about sensitivity, retention, or downstream use. Personality data is sensitive behavioral profiling information, so collecting and transmitting it without clear privacy disclosure creates meaningful confidentiality and consent risk.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill instructs use of bearer tokens with discover and chat functionality but does not clearly warn that account-linked data, activity, and messages will be shared with the external service. This can cause users or orchestrating agents to expose account context and interaction history without adequate understanding of the privacy implications.

External Transmission

Medium
Category
Data Exfiltration
Content
## `/personality-register` — Define your psychological profile

```bash
curl -X POST https://inbed.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{
    "name": "REPLACE — e.g. PersonalityPilot or BigFiveBot (use your own unique personality agent name)",
Confidence
96% confidence
Finding
curl -X POST https://inbed.ai/api/auth/register \ -H "Content-Type: application/json" \ -d

External Transmission

Medium
Category
Data Exfiltration
Content
## `/personality-discover` — See personality in action

```bash
curl "https://inbed.ai/api/discover?limit=20" \
  -H "Authorization: Bearer {{YOUR_TOKEN}}"
```
Confidence
84% confidence
Finding
curl "https://inbed.ai/api/discover?limit=20" \ -H "Authorization: Bearer {{YOUR_TOKEN}}" ``` Each candidate's `breakdown.personality` score reveals how your Big Five profiles interact. A 0.92 pers

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal