Trust

Security checks across malware telemetry and agentic risk

Overview

This is a prompt-only trust and credibility analysis aid with broad triggers but no evidence of hidden code or unsafe access.

Install if you want a general framework for trust and credibility analysis. Treat outputs as practical advice, not professional legal, HR, compliance, clinical, security, or formal risk guidance, and use a specialized expert or skill for high-stakes contexts.

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: 82% confidence
Finding: The trigger conditions are broad enough to activate on many generic requests about relationships, credibility, or skepticism, which can cause the agent to route ordinary conversations into this skill unnecessarily. While the skill content itself is not overtly dangerous, over-triggering can lead to inappropriate scope expansion, misclassification of user intent, and advice being applied in situations better handled by other skills or domain-specific safeguards.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal