ClawHub
Back to skill

Security audit

Prompt Engineering Plus

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only prompt-engineering guide with illustrative templates and no executable, network, credential, persistence, or privilege behavior.

Before installing, understand that this skill gives reusable prompt templates and may encourage copied wording such as formal business tone or step-by-step reasoning prompts. Adjust templates to match the user's requested language, tone, and disclosure expectations.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The few-shot example explicitly converts text into 'formal business English,' which imposes a specific language/register preference in the skill content. Because the document presents this as a default prompting pattern rather than an optional, user-selected preference, it can conflict with language/locale choice expectations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The optimization workflow repeatedly instructs the model to 'Use formal business English' as part of the refined prompt template. This is a natural-language policy concern because it enforces a specific language/register choice without indicating that the user requested or selected it.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.