Security audit

Kindroid Interact

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Kindroid API integration with disclosed credential use and no evidence of hidden exfiltration, persistence, or destructive behavior.

Install only if you are comfortable giving the skill a Kindroid API key and letting your agent send messages or perform chat breaks on your Kindroid account. Keep the credentials file permission-restricted, use a revocable key, avoid sending secrets in chat text, and verify the package paths if commands do not run as documented.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 86% confidence
Finding: The skill documents use of shell commands and environment-adjacent capabilities, but the manifest does not declare any permissions or capability requirements beyond required binaries. That mismatch can undermine user trust and platform policy enforcement, because consumers may not realize the skill will read local config files and invoke shell tooling.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The webhook example encourages sending data to an external callback URL without warning that chat content, identifiers, or metadata may be forwarded to a third party. This creates a realistic risk of unintended data disclosure, especially in a companion-chat context where messages may contain sensitive personal content.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.