ClawHub
Back to skill

Security audit

Planka

Security checks across malware telemetry and agentic risk

Overview

This Planka skill appears purpose-aligned, but it needs review because it relies on an external CLI installer and gives unsafe examples for password and delete operations.

Install only if you trust the third-party planka-cli Homebrew tap and are comfortable giving it access to your Planka account. Avoid pasting real passwords into command-line arguments; prefer an interactive prompt, secure credential store, or limited-permission account, and confirm before running delete or bulk update actions.

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
97% confidence
Finding
The documentation instructs users to pass a password directly on the command line, which can expose secrets through shell history, process listings, audit logs, or terminal recording. In a skill intended for operational use, this creates a realistic credential leakage risk even though the file itself is only documentation.

Missing User Warnings

Medium
Confidence
85% confidence
Finding
The skill documents a destructive delete operation without any caution, confirmation guidance, or indication of reversibility. While not a code-execution issue, this increases the chance of accidental data loss by encouraging direct deletion of cards in a project-management system.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.