ClawHub
Back to skill

Security audit

Openclaw User Intent Refinement

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only skill for clarifying ambiguous user requests before action, with no code, installation behavior, persistence, or hidden data access.

Before installing, understand that this skill may cause the agent to restate or refine unclear requests before acting. That behavior is purpose-aligned, but for destructive, financial, or security-sensitive tasks you should still require explicit confirmation of the final action.

SkillSpector

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
90% confidence
Finding
The usage guidance says only to use the skill 'when the conditions in the description are met,' which is too vague to reliably constrain activation. In an intent-refinement skill, ambiguous triggering can cause the skill to run too broadly, letting it rewrite user requests or execution plans in situations where clarification should instead be requested explicitly, increasing the chance of unsafe or unintended downstream actions.

Static analysis

No suspicious patterns detected.