系统化调试

Security checks across malware telemetry and agentic risk

Overview

This is a debugging-process skill that guides investigation before code changes and does not add hidden tools, persistence, credential use, or data exfiltration.

Install this if you want the agent to slow down and investigate bugs before changing code. Be aware it may activate on many ordinary bug or error reports, so use a more specialized skill explicitly when a task needs a different workflow.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The activation phrases "调试 / debug / 排查问题" are broad, common terms that can match many ordinary user requests unrelated to explicitly invoking this skill. In an agent environment, this can cause unintended routing or invocation, making the skill run in contexts where the user did not opt in and potentially overriding more appropriate specialized skills.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal