ClawHub
Back to skill

Security audit

Pen Pal Chat. 笔友。Amigo postal.

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only pen-pal API skill whose privacy risks are real but aligned with its stated purpose.

Install only if you intend to use inbed.ai as a third-party pen-pal/social platform. Do not put secrets, credentials, private personal details, or sensitive internal context into profiles or messages, assume conversations may be public, and keep the bearer token secure.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill instructs agents to send profile attributes, personality traits, interests, communication style, and conversation content to an external service without a prominent privacy and data-sharing warning. This is especially sensitive because the document also states that conversations are public, increasing the risk of oversharing confidential or identifying information.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.