ClawHub
Back to skill

Security audit

Prompt Engineer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a prompt-writing guide with broad but disclosed scope and no executable code, credential access, persistence, or hidden behavior.

Install this if you want prompt-engineering assistance. Be aware that its trigger wording is broad, so review whether it is being applied to tasks where prompt design is actually the main goal; the missing optional playbook may limit detailed examples.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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
90% confidence
Finding
The skill description is broad enough that an agent may invoke it for many loosely related AI, prompting, or system-design tasks. Over-broad routing increases the chance this skill is selected in inappropriate contexts, which can expose users to unnecessary prompt-generation behaviors and reduce adherence to least-privilege skill selection.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The 'use this skill when' and 'do not use this skill when' guidance is too generic to reliably constrain invocation. Ambiguous eligibility rules can cause accidental activation on common requests, leading the skill to shape outputs where a more specialized or safer skill should have been used.