Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Agent Memory System
v1.0.0Agent 记忆系统设计助手。构建长期记忆、短期记忆、情景记忆架构。触发词：记忆、memory、上下文管理、上下文窗口。
⭐ 0· 53·0 current·0 all-time
by@sky-lv
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Suspicious
medium confidencePurpose & Capability
The SKILL.md implements a hierarchical memory system (short-term, long-term, vector/semantic) which is coherent with the declared purpose. However, the implementation expects an embeddings provider (calls OpenAI embeddings endpoint via process.env.OPENAI_API_KEY) and a local vector store/SQLite database, yet the skill metadata declares no required environment variables or credentials. The omission of the OPENAI_API_KEY requirement is an inconsistency that reduces transparency.
Instruction Scope
The instructions include concrete code that will persist data to a SQLite DB, write to a local Chroma vector store, and send text to the OpenAI embeddings API. Those actions are within a memory system’s scope, but the code builds SQL queries by interpolating user-derived keywords into LIKE clauses (risk of SQL injection) and will send potentially sensitive memory text off-host to OpenAI. The SKILL.md does not warn about privacy, retention, or minimum-data practices.
Install Mechanism
This is an instruction-only skill with no install spec and no code files executed by the registry. That lowers supply-chain risk compared with arbitrary downloads. The runtime instructions still assume installing/using SQLite and a Chroma client, but nothing is being pulled automatically by the skill package itself.
Credentials
The embedded code calls the OpenAI embeddings endpoint using process.env.OPENAI_API_KEY but the skill declares no required env vars or primary credential. Requesting an API key (and thus permission to transmit memory contents externally) is material and should be declared; its absence is a transparency gap. Also, the skill could leak sensitive user data to an external service if deployed without careful access controls.
Persistence & Privilege
The skill does not request always:true, does not claim to modify other skills, and has no install-time persistence declared. It does instruct how to create local DB files and a vector store (expected for a memory system), but it does not assert elevated platform privileges.
What to consider before installing
This skill appears to implement a legitimate agent memory system, but it has important transparency and safety issues you should address before installing: 1) The runtime code calls the OpenAI embeddings API using process.env.OPENAI_API_KEY but the skill metadata does not declare that credential—ask the author to explicitly declare required env vars and explain how API keys are used and stored. 2) The code constructs SQL with string interpolation from user queries (SQL injection risk); require input sanitization or parameterized queries. 3) Embedding calls send memory content to an external service—consider whether memory may contain sensitive data and if you should use a private/local embedding model instead. 4) Request documentation or a link to the repository/homepage, minimal reproducible examples, and any data-retention/privacy controls. If you proceed, use a scoped/dedicated API key, limit retention, and test in an isolated environment first.Like a lobster shell, security has layers — review code before you run it.
latestvk971yw2gc8pwxagx1jrc9hxqvs84jr45
License
MIT-0
Free to use, modify, and redistribute. No attribution required.