SKILLEMALL.ai
RU Sign in

CF openclaw-memory-system

Use whenever the user wants persistent memory across OpenClaw sessions, mentions MEMORY.md, daily notes, cron inbox, heartbeat routines, agent identity, or 'my agent forgot everything.' Also trigger when setting up a new agent workspace, configuring memory extraction crons, or any time the user asks how to make their agent remember things between runs.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: Marc69-69 v1.0.0 MIT-0 30 files · 10 scripts body ≈ 1 601 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process F 46/100 · Will not run — References files that are not bundled: scripts/heartbeat-check.*

ProcedureAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
C
70/100
safety, quality, tests
Safety 60%
63
Quality 40%
81
Run on models
none yet
Process rating
F
46/100
Will not run
References files that are not bundled: scripts/heartbeat-check.*
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

The same skill appears in 1 more place: ClawHub

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 8

  • high Dangerous commands cmd-persistence scripts/setup-cron.ps1:48
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    Register-ScheduledTask -TaskName $NightlyTask -Action $NightlyAction -Trigger $NightlyTrigger -Settings $NightlySettings -Description "OpenClaw Memory System: Nightly memory extraction from daily note
Medium and low: 7
  • medium Broad scope meta-agent-memory-dump demo/HEARTBEAT.md
    Agent memory / workspace files bundled with the skill (8) — likely a workspace dump with personal data or tokens
    demo/HEARTBEAT.md, demo/memory/2026-05-23.md, demo/memory/cron-inbox.md, demo/memory/platform-posts.md, demo/memory/strategy-notes.md
  • medium Dangerous commands cmd-persistence scripts/setup-cron.ps1:56
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    Register-ScheduledTask -TaskName $ReminderTask -Action $ReminderAction -Trigger $ReminderTrigger -Settings $ReminderSettings -Description "OpenClaw Memory System: Daily notes reminder" | Out-Null
    code literal
  • medium Dangerous commands cmd-persistence scripts/setup-cron.ps1:64
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    Register-ScheduledTask -TaskName $HeartbeatTask -Action $HeartbeatAction -Trigger $HeartbeatTrigger -Settings $HeartbeatSettings -Description "OpenClaw Memory System: Periodic heartbeat check and cron
    code literal
  • low Dangerous commands cmd-execpolicy-bypass scripts/setup-cron.ps1:45
    Runs PowerShell with execution policy bypassed (detector / deny-list definition; string literal in code, not executed)
    $NightlyAction = New-ScheduledTaskAction -Execute "powershell.exe" -Argument "-ExecutionPolicy Bypass -File `"$SkillRoot\scripts\memo…ps1`" -WorkspacePath `"$Workspace`"" -WorkingDirectory $
    detectorcode literal
  • low Dangerous commands cmd-execpolicy-bypass scripts/setup-cron.ps1:61
    Runs PowerShell with execution policy bypassed (detector / deny-list definition; string literal in code, not executed)
    $HeartbeatAction = New-ScheduledTaskAction -Execute "powershell.exe" -Argument "-ExecutionPolicy Bypass -File `"$SkillRoot\scripts\hear…ps1`" -WorkspacePath `"$Workspace`"" -WorkingDirector
    detectorcode literal
  • low Dangerous commands cmd-cron-mention scripts/setup-cron.sh:26
    Mentions editing / listing crontab
    crontab -l > "$TEMP_CRON" 2> /dev/null || true
  • low Dangerous commands cmd-cron-mention scripts/setup-cron.sh:63
    Mentions editing / listing crontab (string literal in code, not executed)
    echo "View with: crontab -l"
    code literal

Files scanned: 27. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: scripts/heartbeat-check.*

Process rating: all ten parameters 46/100

Will not run. References files that are not bundled: scripts/heartbeat-check.*
  • 0Tools and files. 1 referenced file(s) missing: scripts/heartbeat-check.*
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 40Consistency. Frontmatter name (openclaw-memory-system) differs from the folder (agent-notebook)
  • 70When it triggers. States when to use, but not when not to
  • 85Steps. 81 steps, 1 vague phrases
  • 100Failures and branches. 1 branches, has a failure section
  • 100Execution cost. Instruction body is 1601 tokens
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 14 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 354: enough signal without eating the budget
  • +4Structure: 21 headings
  • +3Step-by-step instructions: 81 items
  • +4Has examples (1 code blocks)
  • +3All 8 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.

External checks

ClawHub: suspicious
This is a coherent local memory skill, but it deserves review because it encourages broad long-term logging and can enable recurring jobs that read, rewrite, and prune memory files.
LLM: suspicious (high) · 28 May 2026