ClawHub
Back to skill

Security audit

Automation Workflows

Security checks across malware telemetry and agentic risk

Overview

This is a plain instructional automation skill with no executable code, but users should apply privacy and approval safeguards before connecting business tools.

Before installing, understand that this skill may guide your agent to help design automations that connect third-party services and act on business records. Use least-privilege app permissions, test with non-production or low-risk data first, add approval steps before sending messages or changing financial/customer records, and keep logs so failed or duplicate runs can be detected.

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 (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger phrases are broad enough to match common user language such as 'automate' or 'save time', which can cause the skill to activate in contexts where the user did not explicitly request workflow automation guidance. In an agent environment, overbroad invocation increases the chance of unintended execution paths, irrelevant advice, or accidental routing into a skill that discusses cross-tool actions and data movement.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill encourages automations that transfer customer and business data among external services, trigger emails, update CRMs, and perform operational actions, but it does not warn about privacy review, least-privilege access, consent, duplicate execution, or irreversible side effects. This is dangerous because users may implement workflows that leak personal data, corrupt records, or send unintended messages and updates across multiple systems without adequate safeguards.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.