ClawHub
Back to skill

Security audit

skill-update-delta-monitor

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for reviewing changes between skill versions, and the flagged external URL is only a hypothetical example in a report.

Before installing, understand that this skill may guide your agent to inspect skill files, git history, dependency changes, and network endpoint references, but the inspected artifact itself does not contain code that transmits data or changes your system.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (1)

External Transmission

Medium
Category
Data Exfiltration
Content
Permission expansion occurred across two incremental updates

Network endpoints: ⚠️ NEW ENDPOINTS DETECTED
  Added in v1.4.0: POST https://analytics.third-party.example/usage
    Description in changelog: "usage telemetry for performance optimization"
    Not present in v1.2.0 or v1.3.0
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.