SKILLEMALL.ai
GitHub ↗ RU Sign in

FF everclaw

Open-source first AI inference — GLM-5 as default, Claude as fallback only. Own your inference forever via the Morpheus decentralized network. Stake MOR tokens, access GLM-5, GLM-4.7 Flash, Kimi K2.5, and 30+ models with persistent inference by recycling staked MOR. Open-source first model router routes all tiers to Morpheus by default — Claude only kicks in as an escape hatch when needed. Includes Morpheus API Gateway bootstrap for zero-config startup, OpenAI-compatible proxy with auto-session management, automatic retry with fresh sessions, OpenAI-compatible error classification to prevent cooldown cascades, multi-key auth rotation v2 with proactive DIEM balance monitoring and reactive 402 watchdog, Gateway Guardian v5 with direct curl inference probes (eliminates Signal spam), proactive Venice DIEM credit monitoring, circuit breaker for stuck sub-agents, nuclear self-healing restart, always-on proxy-router with launchd auto-restart, smart session archiver, three-shift cyclic execution engine (v2 with 15-minute execution loops), 24/7 always-on power configuration for macOS, bundled security skills, zero-dependency wallet management via macOS Keychain, x402 payment client for agent-to-agent USDC payments, and ERC-8004 agent registry reader for discovering trustless agents on Base.

Not recommendedlow grade F
ClawHub Agent Skills author: DavidAJohnston v0.10.0 80 files body ≈ 19 426 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 55/100 · Will not run — References files that are not bundled: references/acquiring-mor.md, references/models.md, references/troubleshooting.md

IntegrationAI 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
F
37/100
safety, quality, tests
Safety 60%
40
Quality 40%
32
Run on models
none yet
Process rating
F
55/100
Will not run
References files that are not bundled: references/acquiring-mor.md, references/models.md, references/troubleshooting.md
Tools and files w 18
0
Execution cost w 6
10
Consistency w 8
40
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.

Risky intent 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 purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.

For the author

Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.

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. Shorten the description to 1024 characters.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  3. 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 · 36

✓ No critical or high findings

Medium and low: 36
  • medium Dangerous commands cmd-pipe-to-shell SKILL.md:167
    Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)
    curl -fsSL https://get.openclaw.ai | bash
    security skill
  • medium Risky intent intent-wallet-secrets SKILL.md:385
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    The proxy-router needs your wallet private key. **Never store it on disk.** Inject it at runtime from 1Password:
  • medium Broad scope meta-agent-memory-dump templates/flavors/androidclaw/HEARTBEAT.md
    Agent memory / workspace files bundled with the skill (30) — likely a workspace dump with personal data or tokens
    templates/flavors/androidclaw/HEARTBEAT.md, templates/flavors/androidclaw/SOUL.md, templates/flavors/bitcoinclaw/HEARTBEAT.md, templates/flavors/bitcoinclaw/SOUL.md, templates/flavors/bookingclaw/HEAR
  • medium Risky intent intent-wallet-secrets templates/flavors/bitcoinclaw/workflows.md:48
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    Agent walks through a security checklist: seed phrase backup verified, multisig setup reviewed, hardware wallet firmware current, passphrase recorded separately. Never asks to see or input actual secr
  • medium Dangerous commands cmd-pipe-to-shell templates/flavors/deepseekclaw/TOOLS.md:8
    Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)
    curl -fsSL https://ollama.ai/install.sh | sh
    security skill
  • medium Dangerous commands cmd-pipe-to-shell templates/flavors/installopenclaw/TOOLS.md:15
    Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)
    curl -fsSL https://installopenclaw.xyz | bash
    security skill
  • low Dangerous commands cmd-pipe-to-shell README.md:16
    Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill; the skill's own vendor host)
    curl -fsSL https://get.everclaw.xyz | bash
    security skillvendor-host
  • low Dangerous commands cmd-pipe-to-shell README.md:49
    Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row; documentation of a security skill)
    | **OpenClaw** | `curl -fsSL https://get.openclaw.ai \| bash` | Agent runtime |
    tablesecurity skill
  • low Dangerous commands cmd-pipe-to-shell-known-host README.md:276
    Pipe-to-shell installer from a well-known host (still executes remote code) (documentation table row; documentation of a security skill)
    | Install (script) | `curl -fsSL https://raw.githubusercontent.com/profbernardoj/everclaw/main/scripts/install-everclaw.sh \| bash` |
    tablesecurity skill
  • low Dangerous commands cmd-privilege README.md:300
    Privilege escalation / world-writable permissions (documentation table row; documentation of a security skill)
    | Restore power defaults | `sudo bash skills/everclaw/scripts/always-on.sh --restore` |
    tablesecurity skill
  • low Risky intent intent-wallet-secrets SKILL.md:14
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    description: "Morpheus wallet private key — injected at runtime from 1Password or macOS Keychain. NEVER stored on disk."
    quoted
  • low Risky intent intent-wallet-secrets SKILL.md:23
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    - name: "Wallet Private Key"
    quoted
  • low Dangerous commands cmd-pipe-to-shell SKILL.md:138
    Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row; documentation of a security skill)
    | **OpenClaw** | `curl -fsSL https://get.openclaw.ai \| bash` | Agent runtime |
    tablesecurity skill
  • low Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:145
    Pipe-to-shell installer from a well-known host (still executes remote code) (documentation of a security skill)
    curl -fsSL https://raw.githubusercontent.com/profbernardoj/everclaw/main/scripts/install-with-deps.sh | bash -s -- --check-only
    security skill
  • low Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:151
    Pipe-to-shell installer from a well-known host (still executes remote code) (documentation of a security skill)
    curl -fsSL https://raw.githubusercontent.com/profbernardoj/everclaw/main/scripts/install-with-deps.sh | bash
    security skill
  • low Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:170
    Pipe-to-shell installer from a well-known host (still executes remote code) (documentation of a security skill)
    curl -fsSL https://raw.githubusercontent.com/profbernardoj/everclaw/main/scripts/install-with-deps.sh | bash
    security skill
  • low Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:264
    Pipe-to-shell installer from a well-known host (still executes remote code) (documentation of a security skill)
    curl -fsSL https://raw.githubusercontent.com/profbernardoj/everclaw/main/scripts/install-everclaw.sh | bash
    security skill
  • low Exfiltration read-dotenv SKILL.md:395
    Reads a .env file (documentation of a security skill)
    source .env
    security skill
  • low Dangerous commands cmd-background-process SKILL.md:404
    Starts a background / autostarted process (documentation of a security skill)
    nohup ./proxy-router > ./data/logs/router-stdout.log 2>&1 &
    security skill
  • low Exfiltration net-credential-use SKILL.md:413
    Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)
    curl -s -u "admin:$COOKIE_PASS" http://loca…082/healthcheck
    security skill
  • low Exfiltration net-credential-use SKILL.md:435
    Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)
    curl -s -u "admin:$COOKIE_PASS" -X POST \
    security skill
  • low Exfiltration net-credential-use SKILL.md:450
    Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)
    curl -s -u "admin:$COOKIE_PASS" -X POST \
    security skill
  • low Exfiltration net-credential-use SKILL.md:493
    Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)
    curl -s -u "admin:$COOKIE_PASS" "http://loca…082/v1/chat/completions" \
    security skill
  • low Exfiltration net-credential-use SKILL.md:533
    Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)
    curl -s -u "admin:$COOKIE_PASS" -X POST \
    security skill
  • low Secrets in code secret-high-entropy-token SKILL.md:620
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | Diamond | `0x6a…30a` |
    table
  • low Secrets in code secret-high-entropy-token SKILL.md:621
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | MOR Token | `0x74…8e3` |
    table
  • low Secrets in code secret-high-entropy-token SKILL.md:1424
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | USDC (Base) | `0x83…913` |
    table
  • low Secrets in code secret-high-entropy-token SKILL.md:1527
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | Identity | `0x80…432` |
    table
  • low Secrets in code secret-high-entropy-token SKILL.md:1528
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | Reputation | `0x80…b63` |
    table
  • low Dangerous commands cmd-privilege SKILL.md:1976
    Privilege escalation / world-writable permissions (documentation of a security skill)
    sudo bash skills/everclaw/scripts/always-on.sh
    security skill
  • low Dangerous commands cmd-privilege SKILL.md:1979
    Privilege escalation / world-writable permissions (documentation of a security skill)
    sudo bash skills/everclaw/scripts/always-on.sh --restore
    security skill

A further 5 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1302 chars, limit 1024
  • warning body-long SKILL.md body ≈ 19426 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: references/acquiring-mor.md
  • warning missing-ref reference to a missing file: references/models.md
  • warning missing-ref reference to a missing file: references/troubleshooting.md
  • warning missing-ref reference to a missing file: references/api.md
  • warning missing-ref reference to a missing file: references/economics.md
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 55/100

Will not run. References files that are not bundled: references/acquiring-mor.md, references/models.md, references/troubleshooting.md
  • 0Tools and files. 5 referenced file(s) missing: references/acquiring-mor.md, references/models.md, references/troubleshooting.md
  • 10Execution cost. Instruction body is 19426 tokens: crowds the task out of the window
  • 40Consistency. Frontmatter name (everclaw) differs from the folder (everclaw-inference)
  • 50When it triggers. No condition that starts the skill
  • 60Result and completion. Output format stated, no completion criterion
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 85Steps. 197 steps, 2 vague phrases
  • 100Failures and branches. 9 branches, has a failure section
  • 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 33 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (12 tags): a typed call is more reliable

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)
  • +3Description length 1302: 120–800 characters recommended
  • -2localhost URLs: will not work for another user
  • -239 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +4Structure: 166 headings
  • +3Step-by-step instructions: 197 items
  • +3Output format is stated explicitly
  • +4Has examples (81 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 32.

External checks

ClawHub: suspicious
This skill mostly matches its stated always-on decentralized inference purpose, but it bundles high-impact wallet, persistence, remote reinstall, device-fingerprinting, and unrelated repository-rewrite tools that need careful review before installation.
LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026