Hita-Mind & Knowledge
v1.0.0hita 开发的 AI Agent 记忆与知识管理系统。包含 Mind Module（8大分类记忆）和 Knowledge Manager（3层知识库）两个互补模块。Mind Module 存储偏好、决策、教训；Knowledge Manager 存储技巧、方法、规则。适用于 AI Agent 的长期知识积累。触...
⭐ 0· 32·0 current·0 all-time
by@hita126
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description describe an AI memory & knowledge system and the package contains two CLI modules (mind and knowledge) that read/write local JSON stores — this matches expected capabilities. No unrelated credentials, binaries, or surprising dependencies are requested.
Instruction Scope
SKILL.md and module-specific SKILL.md instruct the agent to run local node CLI commands (list, add, search, context, compress). Runtime instructions reference only local files (module index.js and store JSON) and do not instruct reading unrelated system files, environment variables, or sending data externally.
Install Mechanism
No install spec provided (instruction-only skill) and the code has no external download/install steps. package.json lists no dependencies; modules are pure Node.js files. No high-risk install URLs or archive extraction are present.
Credentials
The skill requires no environment variables, no credentials, and no config paths. All persistent data is stored in local JSON files inside the skill directories; this is proportional to a local memory/knowledge manager.
Persistence & Privilege
Skill is not marked always:true and uses only its own local JSON stores. It does persistent writes (store JSON) which are expected for a memory/knowledge skill; it does not modify other skills or system-wide configuration.
Scan Findings in Context
[no_injection_signals] expected: Static pre-scan reported no injection signals. The codebase is local-only and contains no network, child_process, or obfuscated code patterns in the visible files.
Assessment
This package appears internally consistent and implements a local JSON-based memory and knowledge CLI — it does not contact external services or ask for credentials. Before installing, consider: 1) review the included files yourself (they will write to and read from memory-store.json and knowledge-store.json inside the skill directories); 2) avoid storing sensitive secrets in those JSON files; 3) run the code in a sandbox or with limited permissions if you are unsure about the source (the repository owner is unknown); 4) if you plan to let an agent invoke this autonomously, be aware it can write persistent local data (the skill is not always:true, but autonomous invocation is allowed by default).Like a lobster shell, security has layers — review code before you run it.
latestvk97b60gk581djz8bca7m00jbq18441f5
License
MIT-0
Free to use, modify, and redistribute. No attribution required.