Karakeep

Security checks across malware telemetry and agentic risk

Overview

This Karakeep skill is mostly coherent, but it needs review because it handles an account API key, includes deletion examples, and shows a cloud server address that does not match current official Karakeep docs.

Install only if you intend to let an agent manage your Karakeep account. Use a revocable API key, set the server address from your own instance or official Karakeep docs, avoid passing secrets on the command line, and require explicit confirmation before deleting any bookmark or list.

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 (2)

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The skill documents destructive commands such as deleting lists and bookmarks without any caution, confirmation guidance, or recommendations to verify targets first. In an agent context, this increases the chance of accidental irreversible data loss if the model follows examples too literally or executes cleanup actions without explicit user confirmation.

Missing User Warnings

Medium

Confidence: 84% confidence
Finding: The authentication section instructs use of an API key via environment variables or CLI flags but does not warn against exposing secrets in logs, shell history, screenshots, or process listings. In agent workflows, this can lead to credential leakage if the agent echoes commands, includes them in transcripts, or uses insecure flag-based invocation.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal