ClawHub
Back to skill

Security audit

Copy

Security checks for vulnerabilities and agentic risk

Overview

This skill is a copy-operations reference that prints command examples and troubleshooting notes without hidden execution, persistence, or data collection.

Install this as a command-reference skill, but review any generated copy or sync command before running it, especially examples involving sudo, rsync --delete, dd, remote SSH targets, or source-file removal because those can change or delete data if adapted incorrectly.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · scripts/script.sh (reported line 362)May include surrounding context.

sh
Permission Denied:
  Error: cp: cannot open 'file': Permission denied
  Fix:   sudo cp, or fix source permissions
         Check: ls -la file, stat file
         SELinux: ls -Z file, restorecon -v file

Static analysis

No suspicious patterns detected.