Security audit

Potassium

Security checks across malware telemetry and agentic risk

Overview

This package is a disclosed Infomaniak integration that can read or change kDrive, Mail, kChat, and URL-shortener data when configured, with sensible default mutation and credential safeguards.

Install only if you intend to let OpenClaw access your Infomaniak account through INFOMANIAK_TOKEN. Keep blockMutating enabled unless you deliberately want write actions, consider configuring allowedDomains or allowedOperations to limit scope, and enable kChat inbound WebSocket or webhook modes only for channels where automated replies are acceptable.

SkillSpector

By NVIDIA

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Exfiltration Commands

High

Category: Prompt Injection
Content: --- name: kchat-posting description: Post messages to Infomaniak kChat through Potassium's native OpenClaw tools backed by the liquid-potassium Node SDK. Use when an agent needs to find kChat teams or channels, create kChat posts, reply in threads with root ids, or post after resolving a channel while following Infomaniak token safety rules. homepage: https://github.com/OpenCow42/potassium-openclaw user-invocable: true metadata: {"openclaw":{"requires":{"config":["plugins.entries.potassium.enabled"],"env":["INFOMANIAK_TOKEN"]},"primaryEnv":"INFOMANIAK_TOKEN"}}
Confidence: 90% confidence
Finding: Post messages to

Vague Triggers

Medium

Confidence: 86% confidence
Finding: The skill’s activation guidance is very broad, covering many Infomaniak services and generic verbs like inspect or manage, which can cause the agent to invoke this skill for loosely related requests without clear user intent. Over-broad triggering increases the chance of unnecessary access to sensitive enterprise data or execution of actions in the wrong service context.

VirusTotal

60/60 vendors flagged this plugin as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.