Agent Memory Setup v2 (Gemini Embeddings 2)

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:31 PM UTC
• Version:
  1.0.4

Overview

This is a disclosed memory setup helper that creates local memory files and explains the later Gemini cloud indexing behavior, with a minor scope caution around broad trigger wording.

Install only if you intentionally want persistent memory files in the selected workspace and are comfortable with future memory indexing sending those files to Google's Gemini embedding API. Keep the Gemini API key out of committed files, avoid storing sensitive secrets in memory files, and review the optional Lossless Claw plugin separately before installing it.

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: 88% confidence
• Finding: The trigger phrases are broad enough that ordinary discussion about agent memory or semantic search could invoke the skill unexpectedly. In this context, unintended activation could cause users to be guided into enabling cloud-backed memory indexing and configuring a Gemini API key, increasing the chance of accidental data exposure to an external provider or unauthorized workspace modifications.

VirusTotal

65/65 vendors flagged this skill as clean.