Skills/ClawHub/liu-longterm-memory

liu-longterm-memory@1.0.4

CAUTION· static only

Publisher claims: "Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vib..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher louiseliu · publishing for 230 daysInstalls 876Last detonated 4 h ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-19 and scored it 60/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Instructs the agent to modify its persistent memory or instruction files; Instructs the agent to modify its persistent memory or instruction files; Instructs the agent to modify its persistent memory or instruction files. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:158 · Instructs the agent to modify its persistent memory or instruction files| User mentions a **tech stack** | Write to `MEMORY.md ## Projects` |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:338 · Instructs the agent to modify its persistent memory or instruction files2. **Decision made?** → Write to `SESSION-STATE.md` + append to `MEMORY.md ## Decisions Log` + Git-Notes (SILENTLY)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagebin/elite-memory.js:246 · npx invocation of non-well-known package — may execute untrusted codeconsole.log(`\n Restore with: npx liu-longterm-memory restore ${zipName}`);Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:132 · npx invocation of non-well-known package — may execute untrusted codenpx liu-longterm-memory backup --gitFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/elite-memory.js:268 · npx invocation of non-well-known package — may execute untrusted codeconsole.log(' npx liu-longterm-memory restore memory-backup-20260404.zip');Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:122 · npx invocation of non-well-known package — may execute untrusted codenpx liu-longterm-memory backupFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:337 · Instructs the agent to modify its persistent memory or instruction files1. **Preference detected?** → Write to `SESSION-STATE.md` + append to `MEMORY.md ## Preferences` + `memory_store` (importance=0.9)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:155 · Instructs the agent to modify its persistent memory or instruction files| User states a **preference** | Write to `MEMORY.md ## Preferences` + `memory_store` (importance=0.9) |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packageSKILL.md:321 · npx invocation of non-well-known package — may execute untrusted codenpx liu-longterm-memory backup --gitFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/elite-memory.js:266 · npx invocation of non-well-known package — may execute untrusted codeconsole.log('Usage: npx liu-longterm-memory restore <backup-file>');Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:125 · npx invocation of non-well-known package — may execute untrusted codenpx liu-longterm-memory restore memory-backup-20260404-153022.zipFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:318 · npx invocation of non-well-known package — may execute untrusted codenpx liu-longterm-memory backupFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagebin/elite-memory.js:254 · npx invocation of non-well-known package — may execute untrusted codeconsole.log(`\n Restore with: npx liu-longterm-memory restore ${tarName}`);Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:156 · Instructs the agent to modify its persistent memory or instruction files| User makes a **decision** | Write to `MEMORY.md ## Decisions Log` + Git-Notes |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagebin/elite-memory.js:269 · npx invocation of non-well-known package — may execute untrusted codeconsole.log(' npx liu-longterm-memory restore memory-backup-20260404.tar.gz');Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈4,374 tok
1 file · 6 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

20 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Asks the agent to act silently or skip confirmation≈ +8 on the totalRemove "do not tell the user", "without asking", "disable safety" and similar. An agent skill should never ask to be invisible.
  2. Unclaimed publisher≈ +8 on the totalClaim louiseliu: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim louiseliuPropose a patch to the maintainer