Security audit

Quick Context Saver

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a memory-management guide, but its privacy claims do not fully match its optional external sync, callback, and sensitive-memory retention guidance.

Review this before installing if you plan to store confidential context. Treat sync, callback URLs, and Gist backups as external data sharing; keep sync off unless needed, encrypt before export, avoid storing raw secrets or regulated identifiers, and verify the npm dependency source before running global install commands.

SkillSpector

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 (5)

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill introduces callback URLs and network-based behavior without a prominent privacy warning or explicit consent flow, despite marketing itself as local and privacy-protective. Users may unknowingly send memory contents or metadata off-device, creating unexpected data disclosure risks.

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: The GitHub Gist sync feature can transfer local memory data to an external service, but the document does not prominently warn that this breaks the stated '100% local storage' privacy model. In a memory tool that may store sensitive context, that mismatch materially increases the chance of unintentional exfiltration.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The backup example explicitly exports memory data and pushes it to Gist without strong warning about external storage, retention, or the sensitivity of backed-up content. This can lead users to upload confidential memory archives, potentially including secrets or regulated data, to a third-party platform.

Ssd 3

Medium

Confidence: 95% confidence
Finding: The examples normalize storing secrets and sensitive case data in agent-managed memory, which increases the chance of long-term retention, later retrieval, export, or synchronization of confidential information. Even with encryption options, encouraging secret ingestion into memory expands the attack surface and can conflict with least-retention principles.

Ssd 3

Medium

Confidence: 91% confidence
Finding: The skill broadly promotes collecting, tracking, auditing, exporting, and syncing memories that may contain sensitive user data, without strong minimization boundaries. In a memory-management context, this increases privacy and compliance risk because more sensitive information may be retained and moved across storage and network boundaries.

Static analysis

No suspicious patterns detected.