Research Idea

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed business-idea research helper that starts a user-triggered background session, searches the web, saves a local research file, and returns results to the current chat.

Install if you are comfortable with user-triggered background research sessions, web searches about the idea, local storage under `~/clawd/ideas/`, and results being returned to the active chat. Use a private chat for confidential ideas and delete generated sessions or files when they are no longer needed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Confidence
88% confidence
Finding
The template explicitly instructs the agent to create a directory and write a research file under `~/clawd/ideas/{IDEA_SLUG}/research.md` without any user-facing disclosure or confirmation. Although this appears intended for normal skill operation rather than abuse, it still causes persistent local filesystem writes based on user-provided idea data, which can surprise users and may create privacy, storage, or path-handling risks if not clearly bounded.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal