ClawHub
Back to skill

Security audit

Node Inspect Debugger

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign because the scanners report no malicious behavior and identify one data-handling omission, though the scan was partial.

The verdict is benign, not risk-free. Before installing, consider whether you may use heap snapshots containing secrets or personal data; handle any snapshots privately and remove them when no longer needed. The scan was partial because several referenced paths could not be matched to bundled artifacts.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

The heap-snapshot workflow omits a warning that the saved snapshot may contain sensitive application data.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

Heap snapshots can contain credentials, tokens, personal information, and other sensitive values retained in application memory. The workflow recommends saving a snapshot to a predictable /tmp path without warning about its sensitivity or specifying access controls and cleanup, creating a potential disclosure risk if the artifact is accessible to other users or later shared. Heap collection is legitimate in this debugging skill, and no exfiltration is instructed, so this is a handling omission rather than evidence of malicious intent.

Content

No source excerpt is available for this finding.