ClawHub
Back to skill

Security audit

Durable Workflow

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent durable-workflow guide with visible, user-run helper scripts and no hidden automatic behavior.

Reasonable to install for workflow-resilience guidance. Before running or copying the scripts, choose dedicated state, DLQ, output, and lock paths, avoid storing secrets in persisted files, and redact error messages before sending alerts to Telegram or any other external service.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (1)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The manifest description contains broad trigger phrases such as 'automate', 'workflow', 'multi-step', 'retry', and 'handle errors', which can match many ordinary user requests and cause this skill to activate outside its narrow intended scope. Over-broad auto-triggering increases the chance that code patterns involving files, locks, env vars, and external notifications are injected into unrelated tasks, expanding attack surface and causing unintended behavior.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.