Memos Memory Guide Backup
v1.0.0Use the MemOS Lite memory system to search and use the user's past conversations. Use this skill whenever the user refers to past chats, their own preference...
⭐ 0· 99·1 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name and description claim to be a usage guide for MemOS Lite memory tools and the SKILL.md only instructs how and when to call memory_* helper tools (memory_search, task_summary, skill_get, skill_install, memory_timeline, memory_viewer). There are no unrelated environment variables, binaries, or installs required, so the requested capabilities match the stated purpose.
Instruction Scope
Instructions are scoped to searching and fetching user conversation history and to installing/retrieving skills when relevant. The guide asks the agent to generate short search queries from the user's message and call memory_search when auto-recall is empty — this is appropriate for a memory helper. The instructions do not direct the agent to read unrelated system files, request other credentials, or send data to external endpoints beyond the memory viewer URL and built-in memory tools.
Install Mechanism
This is an instruction-only skill with no install spec and no code files, so nothing is written to disk. There is no external download or package installation; install-like behavior mentioned (skill_install) refers to installing other skills via the platform API, which is expected for this domain.
Credentials
The skill requires no environment variables, credentials, or config paths. It does instruct use of platform tools that access stored memories (expected), but it does not request unrelated secrets or broad environment access.
Persistence & Privilege
always:false (default) and autonomous invocation is allowed (platform default). The guide suggests using skill_install to make other skills available — this is a normal platform capability, but installing additional skills increases the agent's future capabilities and attack surface if the agent is allowed to act autonomously. That combination is not itself a misbehavior here, but it's something to be aware of.
Assessment
This skill is an instruction-only guide that appears coherent and does not ask for credentials or install code. Before enabling it: (1) consider provenance — the source/homepage is unknown, so verify you trust the registry owner; (2) confirm platform controls for autonomous agent actions and skill_install (decide whether the agent should be allowed to install other skills without explicit user approval); (3) understand privacy implications — using the memory tools will access and surface your stored conversations, so confirm your memory retention and sharing policies; and (4) check how the memory_viewer URL is presented and whether opening it exposes data outside your control. If you require stronger guarantees, only enable the skill when you can audit or trust its owner and when agent-autonomy/installation policies match your risk tolerance.Like a lobster shell, security has layers — review code before you run it.
latestvk9723gfksp7wxajmrw4qmyq8n583hgk2
License
MIT-0
Free to use, modify, and redistribute. No attribution required.