ClawHub
Back to skill

Security audit

Anti-Laziness Protocol

Security checks for vulnerabilities and agentic risk

Overview

This is a guidance-only quality-control skill that may be heavy-handed, but it does not show hidden access, credential use, network transfer, or destructive behavior.

Install this if you want an agent to follow a strict evidence-first review process. Be aware it may activate broadly for analysis or verification work, may steer behavior toward Chinese-language instructions, and may create temporary progress notes unless your agent environment limits that.

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 (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger section activates on broad categories such as 'technical research', 'document validation', 'detailed analysis', and 'any work requiring verification'. These conditions are vague and expansive, which can cause the skill to load in many unrelated contexts and unexpectedly override agent behavior, increasing the chance of prompt-scope interference or denial of intended workflow.

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
The skill metadata and content are written in Chinese and describe behavior for agents without indicating user language choice or a justified locale requirement. In a multi-user or multilingual environment, this can create misunderstanding of constraints and accidental misapplication of the skill, which is primarily a reliability and governance issue rather than a direct exploit primitive.

Static analysis

No suspicious patterns detected.