Memory Lifecycle

Security checks across malware telemetry and agentic risk

Overview

This instruction-only skill helps manage Basic Memory note status changes and does not show hidden, deceptive, or unrelated behavior.

Install this if you want an agent to archive, reactivate, or update Basic Memory notes. Review matched entities and destination folders before approving bulk moves, because ambiguous completion language could otherwise cause an unintended note status change.

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 (2)

Vague Triggers

Medium

Confidence: 83% confidence
Finding: The skill description and activation guidance are broad enough that an agent could invoke this skill when a user uses common status words in ordinary conversation, not necessarily when they intend a file lifecycle operation. In this skill, mistaken activation can lead to state-changing actions like moving notes or updating frontmatter, which creates integrity risk in the user's memory store even without malicious intent.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger list relies on generic terms like 'done', 'finished', and 'completed' without boundaries showing when those words should not activate the skill. Because the skill performs mutating operations on notes, an over-broad trigger surface increases the chance of accidental archival, reactivation, or metadata edits from ambiguous user language.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal