Structured Life Review

Security checks across malware telemetry and agentic risk

Overview

This is a text-only life-review conversation guide with no code, data access, persistence, or hidden authority, though it can involve sensitive memories.

This appears safe to install from the reviewed artifacts. Use it with care for conversations involving grief, trauma, loss, or visible distress, and consider pairing it with an emotional-safety skill or qualified human support for sensitive or clinical contexts.

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

Medium

Confidence: 90% confidence
Finding: The guide encourages emotionally probing autobiographical memory work and even notes to follow emotional content and pause when distress appears, but it does not explicitly warn users that reminiscence can surface distressing or traumatic memories or define safety boundaries for non-clinical use. In a conversational agent, this omission can lead the system to elicit painful material without informed consent, appropriate guardrails, or escalation guidance.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal