ClawHub
Back to skill

Security audit

Security Best Practices

Security checks for vulnerabilities and agentic risk

Overview

This skill is a transparent security-review helper that stores optional local review context only after user consent.

Install this if you want a reusable security-review workflow. Before enabling memory, decide whether you are comfortable storing review preferences, findings, and accepted-risk notes in ~/security-best-practices/; decline persistence if project security context should remain session-only.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Hidden Instructions

High
Category
Prompt Injection
Content
integration: pending

## Context
<!-- Threat model and business constraints -->
<!-- Critical systems and data sensitivity notes -->

## Review Preferences
Confidence
70% confidence
Finding
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The invocation text says to activate when the user requests 'security guidance, hardening, risk triage, or remediation planning,' which is a broad natural-language condition rather than a specific trigger set. It does not provide exclusion conditions or negative examples, so ordinary requests for general guidance may overlap and cause unintended activation.

Static analysis

No suspicious patterns detected.