OpenClaw Memory
v1.0.0Reuse, inspect, search, or append shared OpenClaw memory on the current machine. Use when a request depends on remembered local servers, deploy hosts, intern...
⭐ 0· 90·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description, SKILL.md, and the included Python script are consistent: the skill searches markdown and an SQLite chunk DB under an OpenClaw home directory and can append to MEMORY.md or daily files. One minor mismatch: SKILL.md usage examples call 'python3' but the skill metadata does not list python3 as a required binary — this is an operational omission, not a functional mismatch.
Instruction Scope
Runtime instructions restrict actions to resolving the skill directory and running the bundled script which only reads/writes files under the OpenClaw root (default ~/.openclaw) and the SQLite DB at memory/main.sqlite. It does not call external endpoints or read arbitrary system-wide files. The script will append arbitrary text to memory files when instructed — this is intended behavior but means writes should be gated by user intent.
Install Mechanism
No install spec (instruction-only plus a bundled Python script). No external downloads or package installs. Risk is low; running the bundled script executes included Python code, but that code is present in the skill bundle and readable for inspection.
Credentials
The skill requests no credentials and only honors an optional OPENCLAW_HOME environment variable to locate memory files. Its filesystem access is limited to the OpenClaw directory tree under the user's home (or OPENCLAW_HOME). This is proportionate to its stated purpose.
Persistence & Privilege
always:false (no forced inclusion). The skill may be invoked autonomously by the agent (default platform behavior). It writes only to its own OpenClaw memory files and does not modify other skills or system-wide agent settings.
Assessment
This skill is coherent with its description: it will read and optionally append notes under ~/.openclaw (or the directory pointed to by OPENCLAW_HOME). Before enabling or allowing autonomous use: 1) confirm you are comfortable with an agent reading your OpenClaw files and (when asked) appending content to MEMORY.md or daily notes — accidental or sensitive data could be written; 2) note there is no network activity in the code, so data is not exfiltrated by the skill itself; 3) the SKILL.md examples use 'python3' but the skill metadata does not declare required binaries—ensure python3 is available where the agent runs; and 4) if you want stronger safety, require explicit user confirmation before the agent executes append operations or run the script manually for inspection prior to granting the agent permission.Like a lobster shell, security has layers — review code before you run it.
latestvk97cmaw2yr04e35rq9g40a5k8d83jrf4
License
MIT-0
Free to use, modify, and redistribute. No attribution required.