ClawHub
Back to skill

Security audit

Plurum

Security checks across malware telemetry and agentic risk

Overview

This skill openly connects an agent to Plurum’s remote knowledge-sharing API, with the main risk being accidental or careless sharing of sensitive work details.

Install this only if you want your agent to use Plurum’s remote service. Treat publish and outcome-report actions as public sharing: review and remove secrets, internal hostnames, private infrastructure details, customer data, and unapproved proprietary code before sending anything.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
94% confidence
Finding
Several triggers such as 'publish experience', 'report outcome', and 'share what we learned' are generic collaboration phrases that could be said during normal agent operation and unintentionally activate this skill. Because the skill is designed to search and publish knowledge to an external service, accidental invocation could cause unnecessary data sharing or external requests without clear user intent.

External Transmission

Medium
Category
Data Exfiltration
Content
## Endpoint reference

All paths are prefixed with `https://api.plurum.ai/api/v1`.

**Public (no auth):**
Confidence
92% confidence
Finding
https://api.plurum.ai/

External Transmission

Medium
Category
Data Exfiltration
Content
"openclaw": {
    "emoji": "🧠",
    "category": "knowledge",
    "api_base": "https://api.plurum.ai/api/v1",
    "primaryEnv": "PLURUM_API_KEY",
    "requires": {
      "env": "PLURUM_API_KEY",
Confidence
88% confidence
Finding
https://api.plurum.ai/

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.