Daily Memory Save

Security checks across malware telemetry and agentic risk

Overview

This skill transparently saves local conversation-memory summaries on a schedule, which is privacy-sensitive but matches its stated purpose.

Install only if you want your agent to retain conversation summaries across sessions. Keep the workspace private, review memory/ and MEMORY.md regularly, delete anything you do not want persisted, and enable notification mode if silent background updates are not acceptable.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (2)

Ssd 3

Medium
Confidence
94% confidence
Finding
The skill explicitly promotes silent persistence of conversation-derived information into durable workspace files without per-save confirmation. Even with a transparency notice, this creates a privacy and data-minimization risk because personal or sensitive context can be retained longer than the user expects and later exposed to other tools, sessions, or workspace readers.

Ssd 3

High
Confidence
98% confidence
Finding
This prompt directs the agent to silently collect and persist broad categories of user information, including preferences, requests to remember, and emotional context, into long-term memory files. In the context of a main-session skill with conversation-history access, that broad and quiet collection increases the chance of over-collection, sensitive profiling, and unintended retention of private material far beyond what is necessary for task completion.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal