Smart Memory Query

• Outcome: Pass
• Latest audit: May 28, 2026 at 9:01 AM UTC
• Version:
  1.0.0

Overview

This skill only teaches the agent to search stored memory more often, and that broad behavior is disclosed and matches its stated purpose.

Install this only if you want your agent to proactively consult stored memories across many interactions. Review your saved memories for sensitive or stale content, because this skill may bring prior personal or project context into routine tasks more often than a narrowly triggered memory skill.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The skill is configured with always: true and broad triggers such as any new task, prior-context reference, or proper noun, which will cause memory_search to run on a large fraction of normal conversations. This creates unnecessary retrieval of stored memory, increasing privacy exposure and the chance that unrelated historical context influences responses or leaks into tasks where it is not needed.

VirusTotal

64/64 vendors flagged this skill as clean.