Memory Landscape Review

Security checks across malware telemetry and agentic risk

Overview

This instruction-only skill coherently reviews memory files and proposes cleanup without hidden execution or automatic edits.

Before installing, be comfortable letting the agent read your repository memory files and auto-memory. Review proposed promotions carefully because approved edits could make sensitive or personal instructions durable.

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: 92% confidence
Finding: The manifest describes the skill as reviewing and reorganizing "memory layers" and provides a default prompt, but it does not define specific trigger phrases, activation boundaries, or exclusion conditions. This ambiguity can cause unintended invocation because the scope of when the skill should activate is not clearly constrained.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal