YC New Way

Security checks across malware telemetry and agentic risk

Overview

This is a planning-only startup workflow skill with templates and no hidden code, data access, or unsafe automation.

Reasonable to install as a startup planning aid. Before using any separate analytics, email capture, SEO, newsletter, or community-posting tools suggested by the workflow, review their privacy settings, platform rules, and disclosure requirements.

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

Low
Confidence
85% confidence
Finding
The description lists several activation conditions, but "turn a vague idea into a testable plan" is broad enough to match many ordinary ideation or planning conversations outside this specific YC playbook context. The file does not provide exclusion conditions or negative examples to clarify when the skill should not activate.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal