Comprehensive Tech Documentation

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only documentation skill that reads project files to generate Markdown docs, with no hidden execution, credential use, or destructive behavior found.

Use this skill on a clearly chosen project or folder. Exclude secrets, private notes, customer data, and environment files from the documentation scope, and review generated Markdown before committing or sharing it.

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
92% confidence
Finding
The trigger phrases include broad, generic requests like 'Explain how this works' and 'Document the architecture', which could cause the skill to activate in contexts where the user did not explicitly request this specific capability. In an agentic system, overly broad routing can lead to unintended file reading, documentation generation, or disclosure of internal project structure beyond the user's intent.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal