Memory Search
v1.0.0Search and retrieve relevant information from your indexed memory files using semantic queries and direct file reads for context.
⭐ 4· 2.7k·40 current·42 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
The skill declares two tools (memory_search, memory_get) and the SKILL.md only instructs how to use those tools to find and read indexed memory files. There are no unrelated env vars, binaries, or install steps requested. Minor note: the skill has no description or homepage, which reduces transparency but does not create an incoherence.
Instruction Scope
Runtime instructions stay within the stated purpose: search indexed memory and fetch ranges for context. The doc explicitly forbids reading files via shell and warns not to try to configure the indexer. It does reference session transcripts (if enabled), which is expected for a memory helper but is privacy-sensitive.
Install Mechanism
Instruction-only skill with no install spec or code files — lowest-risk footprint. Nothing will be downloaded or written to disk by an installer.
Credentials
No environment variables, credentials, or config paths are requested. The only resources accessed are the user's indexed memory files and session transcripts as described — appropriate for the stated functionality but privacy-sensitive.
Persistence & Privilege
The skill does not request always:true and has default autonomous-invocation allowed. Autonomous invocation is normal, but note that an autonomously-invoking skill that can read personal memory files has a meaningful privacy blast radius; consider whether you trust the skill author.
Assessment
This skill appears to do what it says: use the platform's memory_search and memory_get tools to read your indexed memory files and (if enabled) session transcripts. Before installing, consider: 1) the publisher is unknown and there is no homepage or description — ask the author for provenance and audit info; 2) the skill will access sensitive personal data (MEMORY.md, memory/*.md, transcripts) — confirm you are comfortable with that access and how those files are stored/retained; 3) verify whether memory reads stay local to the agent or are sent to any external endpoints (the SKILL.md implies local indexed search, but the implementation/runtime details matter); 4) if you need stricter limits, restrict autonomous invocation or review platform logs of memory access. If you want higher confidence, request the skill author's contact, repository/homepage, or a signed manifest showing how the memory_search/memory_get plumbing is implemented.Like a lobster shell, security has layers — review code before you run it.
latestvk9796e9ehvvdeg04cxnk2d9bkh80sq1c
License
MIT-0
Free to use, modify, and redistribute. No attribution required.