Brainstorm

Security checks across malware telemetry and agentic risk

Overview

This is a coherent brainstorming skill that may create and commit design documents, which is disclosed and aligned with its purpose.

Install only if you are comfortable with the agent reading relevant project files and creating design docs in your repository. Review the generated document and explicitly approve any git commit, branch creation, or coding step before allowing it to proceed.

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: 90% confidence
Finding: The skill explicitly instructs the agent to write a design document into the repository and then commit it to git, but it does not require obtaining clear user confirmation immediately before modifying files. In an agent setting, repository writes are side effects, so omitting an explicit safety gate can lead to unintended file changes or commits in the user's workspace.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal