ClawHub
Back to skill

Security audit

zayn-clarify

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only skill for drafting requirement-clarification questions, with no hidden execution, persistence, or data-transfer behavior found.

Reasonable to install for customer requirement clarification. Because it is marked as a draft, users should review outputs before sending them to customers and avoid including sensitive regulated data unless their normal workspace policy allows it.

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
88% confidence
Finding
The invocation template tells the operator to call CLARIFY() but does not define when the skill should be used, when it must not be used, or what preconditions must be checked first. In an agent setting, this can cause overuse, misuse on out-of-scope requests, or accidental forwarding of sensitive/problematic inputs into the skill without a boundary check.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.