SKILLEMALL.ai
GitHub ↗ RU Sign in

BB vm-memory-oracle

Production-grade memory persistence and lifecycle management for VM-hosted OpenClaw agents. Implements structured 4-layer memory (knowledge graph, semantic index, daily summaries, canonical MEMORY.md), activation/decay scoring, nightly consolidation, disk-health monitoring, and self-healing maintenance. Fully local — zero network calls, zero cloud dependencies.

ClawHub Agent Skills author: Sharoon Sharif v2.0.0 MIT-0 9 files · 1 script body ≈ 2 130 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 65/100 · Nearly there — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureInfrastructureAI 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
B
83/100
safety, quality, tests
Safety 60%
90
Quality 40%
73
Run on models
none yet
Process rating
B
65/100
Nearly there
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands 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 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.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 6

✓ No critical or high findings

Medium and low: 6
  • medium Dangerous commands cmd-persistence examples/basic-usage.md:89
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (test fixture / example file)
    cat /etc/cron.d/openclaw-vm-memory-oracle
    fixture
  • low Risky intent intent-offensive-security README.md:175
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | Privilege escalation | Never uses sudo or su. |
  • low Risky intent intent-offensive-security SECURITY.md:25
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - **No privilege escalation.** This skill never uses `sudo`, `su`, `pkexec`,
  • low Dangerous commands cmd-persistence SECURITY.md:46
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation table row; documentation of a security skill)
    | `/etc/cron.d/openclaw-vm-memory-oracle` | Write | Cron job registration |
    tablesecurity skill
  • low Risky intent intent-offensive-security SKILL.md:274
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - **No elevation**: This skill never uses sudo, su, or any privilege escalation.

A further 1 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 65/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 100Tools and files. No external tools needed
  • 100Steps. 33 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2130 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

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
  • +2Single-language instructions
  • +3Description length 363: enough signal without eating the budget
  • +4Structure: 16 headings
  • +3Step-by-step instructions: 33 items
  • +4Has examples (9 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.

External checks

ClawHub: suspicious
This is a coherent local memory skill, but it needs review because it installs persistent system cron jobs and weakly scopes sensitive memory storage.
LLM: suspicious (high) · VirusTotal: · 29 May 2026