ClawHub
Back to skill

Security audit

Bootstrap Review

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed review helper for agent boot files and only writes staged drafts or live changes when the user asks.

Before installing, be aware that the skill is designed to read agent boot files and registry-listed personal or workspace context. Use it when you want that review, and only approve registry edits, staged drafts, or live boot-file rewrites when they match your intended agent setup.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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)

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 26)May include surrounding context.

md
- optional staged replacement drafts

Keep this skill review-first.
Do not silently rewrite live boot files.
Default to audit + recommendations.
Only produce staged replacement drafts if the user asks.
Do not write in place unless the user explicitly requests it.

Static analysis

No suspicious patterns detected.