memory-engine-3layer@6.0.0
CAUTION· static onlyPublisher claims: "Memory guardian for OpenClaw — three-layer anti-amnesia with capacity management. v6.0: MEMORY.md soft cap (5000 chars) + USER.md cap (1500 chars) prevent pr..." Observed in sandbox: static analysis only — behavior not yet observed.
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 67/100 (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 onlyThis 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
console.log(JSON.stringify(output));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.console.log(output);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.│ memory-write.js → append daily log / MEMORY.md│Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.* v6.0: MEMORY.md soft cap (5000 chars), USER.md auto-update (1500 chars),Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.* node memory-write.js --snapshot # snapshot MEMORY.md before compactionFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.(single command: health check + index update + MEMORY.md content)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.* memory-write.js v6.0.0 — Write daily logs + MEMORY.md + USER.md + health checkFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.│ memory-write.js → daily log + MEMORY.md │Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.> **⚠️ Important**: Do NOT instruct memory-flush to write MEMORY.md or run exec commands.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.For deeper consolidation (merging semantically similar entries), manually edit MEMORY.md.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.### Step 4: Add rules to AGENTS.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.if kill -0 "$WATCHER_PID" 2>/dev/null; thenFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.node "$SCRIPT_DIR/memory-write.js" --workspace "$WORKSPACE" --today "[auto-restore] MEMORY.md restored from snapshot — was wiped to ${CORE_SIZE}B" --tag warningFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…&& !coreText && !userText) { console.error('Usage:\n --today "text" [--tag t] Append daily log\n --core "text" [--section s] Append MEMORY.md\n --user "text" Append USER.md\n --snapshot Snapshot MEMORY.md\n --status …Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.│ • MEMORY.md integrity │ │ • forces AI to write │Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Cost to the agent
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
13 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim zacko2o: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.