ClawHub
Back to skill

Security audit

ia-debugging

Security checks across malware telemetry and agentic risk

Overview

This is a coherent debugging workflow skill with a small diagnostics script that gathers limited local environment details for troubleshooting, with no evidence of hidden network transfer or destructive behavior.

Before installing, understand that this skill may guide your agent to run local tests and debugging commands, and its optional diagnostics script can expose repository metadata such as paths, username, and git remote URL. Review or redact diagnostic reports before sharing them outside your workspace.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
86% confidence
Finding
The skill is presented as a debugging workflow, but it explicitly instructs use of a diagnostics script that captures environment state and mentions collecting repository, configuration, and environment details. That expands behavior beyond pure debugging guidance into potentially sensitive data collection, creating a risk of over-collection and leakage of secrets, internal URLs, filesystem paths, or repository metadata if the report is shared, logged, or sent to other tools.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.