Systematic Debugging

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only debugging guide; its trigger words are broad, but it does not request hidden access, credentials, persistence, or unsafe automatic actions.

Install this if you want a structured debugging workflow. Be aware it may activate on common words like bug or error, and review any suggested commands or code edits before running them, especially commands that inspect logs or change files.

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 (2)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The description auto-triggers on very common terms like 'bug', 'error', 'debug', and 'fix this', which can cause the skill to activate in many normal conversations without clear user intent. Over-broad activation increases the chance of inappropriate invocation, context hijacking, and unintended steering of the agent's behavior.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The trigger list consists of ambiguous, high-frequency phrases with no explicit gating rules, making activation boundaries unclear. This can lead to accidental invocation during unrelated support, coding, or conversational tasks, which may override or derail the agent's intended workflow.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal