Security audit

灵芯派记忆守护者为OpenCode AI助手提供记忆持久化，专为灵芯派低资源环境设计，支持Gitee云端同步

Security checks for vulnerabilities and agentic risk

Overview

This skill has a coherent memory-sync purpose, but it appears to store and push potentially sensitive agent memory to Gitee and includes a plaintext credential exposure.

Install only if you deliberately want agent memory stored locally and synchronized to a Gitee repository. Use a private repository, review files before pushing, avoid storing secrets or private chat content, and remove or rotate any plaintext credentials found in the package before use.

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 (6)

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The description explicitly states that the skill provides persistent memory and cross-session synchronization, but it does not clearly disclose the privacy and data-handling implications of storing and syncing user context. Users may install and use the skill without understanding that potentially sensitive conversational data could be retained or propagated across environments, increasing the risk of unintended disclosure.

Missing User Warnings

High

Confidence: 99% confidence
Finding: The file directly discloses a system username and password in plaintext, which is a genuine credential exposure issue. Even if intended as internal convenience documentation, embedding live access credentials in a skill package makes unauthorized access much easier if the file is shared, indexed, logged, or reused in another environment.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The README explicitly states that conversation context is automatically persisted locally and synchronized to Gitee, but it does not warn users that chat transcripts may contain secrets, personal data, credentials, or proprietary information. In an agent skill context, persistent storage plus remote backup increases the chance of unintended disclosure because users may not realize sensitive prompts and outputs are being retained and transmitted off-device.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill explicitly promotes persistent memory with Gitee cloud synchronization, but it does not warn users that conversation history, configuration details, or other sensitive notes may be committed and pushed to a third-party remote repository. In a memory-persistence skill, this omission is security-relevant because the primary function is to store and sync potentially sensitive assistant context, increasing the likelihood of accidental data exposure.

Missing User Warnings

Medium

Confidence: 98% confidence
Finding: The installation steps instruct the user to add a remote and push the memory repository to Gitee without any explicit warning, confirmation step, or guidance on repository privacy. Because the synced files are described as persistent memory and daily logs, users may unknowingly upload sensitive operational context, credentials, personal data, or proprietary information to a remote service.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The script unconditionally pushes the contents of $HOME/.opencode-memory to the configured remote repository, which can transmit sensitive memory data off-host without an explicit confirmation step, preview, or privacy warning. In a memory-sync context this is especially risky because the directory may contain personal data, secrets, prompts, or other sensitive artifacts that users may not realize are being uploaded.

Static analysis

No suspicious patterns detected.