FOUDF - 五算子通用决策框架

Security checks across malware telemetry and agentic risk

Overview

This is a text-only decision-analysis framework with a broad activation trigger but no code, system access, persistence, or data handling.

Install this as a reasoning template, not as expert medical, legal, financial, or mental-health advice. Consider invoking it explicitly for complex decisions, and ask the agent to preserve your preferred language and cite reliable sources when making probability or risk claims.

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: 96% confidence
Finding: The manifest trigger is defined as activating on broadly described 'complex decision' requests, which can match a very large fraction of normal user prompts. This creates overreach risk: the skill may activate unexpectedly, steer conversations into its framework without user consent, and crowd out more appropriate domain-specific or safer handling logic.

VirusTotal

No VirusTotal findings

View on VirusTotal