FD everclaw

AI inference you own, forever powering your OpenClaw agents via the Morpheus decentralized network. Stake MOR tokens, access Kimi K2.5 and 30+ models, and maintain persistent inference by recycling staked MOR. 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 profile rotation for Venice API keys, Gateway Guardian v4 with billing-aware escalation, through-OpenClaw inference probes, proactive Venice DIEM credit monitoring, circuit breaker for stuck sub-agents, and nuclear self-healing restart, always-on proxy-router with launchd auto-restart, smart session archiver to prevent dashboard overload, 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 recommendedcritical or high security findings · low grade F

modbender/skill-library-mcp Agent Skills author: modbender MIT 29 files · 13 scripts body ≈ 16 266 tokens Open the sourcegithub.com↗ analyzed 2 d ago

AI inference you own, forever powering your OpenClaw agents via the Morpheus decentralized network.

As a process D 45/100 · Unfinished process — weak spots: when it triggers, inputs and preconditions, consistency

Integration AI 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

23/100

safety, quality, tests

Safety 60%: 0
Quality 40%: 58
Run on models: none yet

Process rating

45/100

Unfinished process

Inputs and preconditions w 11: 0
Execution cost w 6: 10
When it triggers w 12: 20

the three weakest of ten parameters · all ten

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.

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

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.

How to improve

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.
Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.

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 · 87

high Dangerous commands cmd-persistence scripts/install-proxy.sh:83

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl load "$LAUNCH_AGENTS/com.morpheus.router.plist" 2>/dev/null
```
high Dangerous commands cmd-persistence scripts/install-proxy.sh:85

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl load "$LAUNCH_AGENTS/com.morpheus.proxy.plist" 2>/dev/null
```
high Dangerous commands cmd-persistence scripts/install-proxy.sh:86

Persistence mechanism (cron / launchd / scheduled task / autorun registry)
```
launchctl load "$LAUNCH_AGENTS/ai.openclaw.guardian.plist" 2>/dev/null
```

Medium and low: 84

medium Exfiltration net-credential-use scripts/balance.sh:23

Credential used in a network call (verify the destination is the intended service)
```
BALANCE=$(curl -s -u "admin:$COOKIE_PASS" "${API_BASE}/blockchain/balance" 2>/dev/null || echo "{}")
```
medium Exfiltration net-credential-use scripts/balance.sh:47

Credential used in a network call (verify the destination is the intended service)
```
ALLOWANCE=$(curl -s -u "admin:$COOKIE_PASS" "${API_BASE}/blockchain/allowance?spender=0x6a…30a" 2>/dev/null || echo "{}")
```
medium Exfiltration net-credential-use scripts/balance.sh:60

Credential used in a network call (verify the destination is the intended service)
```
SESSIONS=$(curl -s -u "admin:$COOKIE_PASS" "${API_BASE}/blockchain/sessions" 2>/dev/null || echo "[]")
```
medium Exfiltration net-credential-use scripts/chat.sh:64

Credential used in a network call (verify the destination is the intended service)
```
SESSIONS_RESPONSE=$(curl -s -u "admin:$COOKIE_PASS" "${API_BASE}/blockchain/sessions" 2>/dev/null || echo "[]")
```
medium Exfiltration net-credential-use scripts/chat.sh:85

Credential used in a network call (verify the destination is the intended service)
```
curl -s -u "admin:$COOKIE_PASS" "${API_BASE}/v1/chat/completions" \
```
medium Exfiltration net-credential-use scripts/chat.sh:95

Credential used in a network call (verify the destination is the intended service)
```
RESPONSE=$(curl -s -u "admin:$COOKIE_PASS" "${API_BASE}/v1/chat/completions" \
```
medium Exfiltration net-credential-use scripts/diagnose.sh:273

Credential used in a network call (verify the destination is the intended service)
```
router_health=$(curl -s --max-time 5 -u "admin:$cookie_pass" http://loca…082/healthcheck 2>/dev/null || echo "")
```
medium Dangerous commands cmd-persistence scripts/diagnose.sh:288

Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
```
fix "Start it: launchctl load ~/Library/LaunchAgents/com.morpheus.router.plist"
```
code literal
medium Dangerous commands cmd-persistence scripts/diagnose.sh:304

Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
```
fix "Start it: launchctl load ~/Library/LaunchAgents/com.morpheus.proxy.plist"
```
code literal
medium Exfiltration net-credential-use scripts/diagnose.sh:369

Credential used in a network call (verify the destination is the intended service)
```
balance_json=$(curl -s --max-time 5 -u "admin:$cookie_pass" http://loca…082/blockchain/balance 2>/dev/null || echo "")
```
medium Dangerous commands cmd-persistence scripts/diagnose.sh:477

Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
```
local plist="$HOME/Library/LaunchAgents/${svc}.plist"
```
code literal
medium Dangerous commands cmd-persistence scripts/diagnose.sh:480

Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
```
fix "Load: launchctl load $plist"
```
code literal
medium Dangerous commands cmd-pipe-to-shell scripts/gateway-guardian.sh:266

Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)
```
curl -fsSL "$INSTALL_URL" | bash >> "$LOG_FILE" 2>&1 || nuclear_rc=$?
```
security skill
medium Risky intent intent-wallet-secrets scripts/mor-launch-headless.sh:4

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
```
# Retrieves wallet private key from 1Password at runtime via macOS Keychain.
```
medium Exfiltration net-credential-use scripts/session.sh:75

Credential used in a network call (verify the destination is the intended service)
```
RESPONSE=$(curl -s -u "admin:$COOKIE_PASS" -X POST \
```
medium Exfiltration net-credential-use scripts/session.sh:100

Credential used in a network call (verify the destination is the intended service)
```
RESPONSE=$(curl -s -u "admin:$COOKIE_PASS" -X POST \
```
medium Exfiltration net-credential-use scripts/session.sh:115

Credential used in a network call (verify the destination is the intended service)
```
RESPONSE=$(curl -s -u "admin:$COOKIE_PASS" "${API_BASE}/blockchain/sessions")
```
medium Risky intent intent-wallet-secrets scripts/start.sh:50

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
```
# Retrieve wallet private key
```
medium Exfiltration net-credential-use scripts/start.sh:108

Credential used in a network call (verify the destination is the intended service)
```
HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" -u "admin:$COOKIE_PASS" "http://loca…082/healthcheck" 2>/dev/null || echo "000")
```
medium Dangerous commands cmd-pipe-to-shell scripts/swap.sh:10

Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment)
```
# Requires: Foundry (cast) installed. Install: curl -L https://foundry.paradigm.xyz | bash && foundryup
```
comment
medium Dangerous commands cmd-pipe-to-shell scripts/swap.sh:92

Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)
```
echo "   curl -L https://foundry.paradigm.xyz | bash"
```
code literal
medium Risky intent intent-wallet-secrets SKILL.md:256

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:
```

low Dangerous commands cmd-pipe-to-shell-known-host docs/index.html:399

Pipe-to-shell installer from a well-known host (still executes remote code) (detector / deny-list definition)

<p style="font-size: 13px; color: var(--text-muted); margin-top: 8px;">Or: <code style="font-size: 12px;">curl -fsSL https://raw.githubusercontent.com/profbernardoj/everclaw/main/scripts/install-everc

detector

low Dangerous commands cmd-pipe-to-shell-known-host docs/index.html:488

Pipe-to-shell installer from a well-known host (still executes remote code) (detector / deny-list definition)

<p style="font-size: 13px; color: var(--text-muted); margin-top: 8px;">Or: <code style="font-size: 12px;">curl -fsSL https://raw.githubusercontent.com/profbernardoj/everclaw/main/scripts/install-everc

detector

low Dangerous commands cmd-pipe-to-shell-known-host README.md:20

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 Dangerous commands cmd-pipe-to-shell-known-host README.md:211

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 Secrets in code secret-high-entropy-token references/acquiring-mor.md:96

High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
```
| MOR | `0x74…8e3` | 18 |
```
table
low Secrets in code secret-high-entropy-token references/acquiring-mor.md:98

High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
```
| USDC | `0x83…913` | 6 |
```
table
low Secrets in code secret-high-entropy-token references/acquiring-mor.md:99

High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
```
| USDT | `0xfd…bb2` | 6 |
```
table
low Exfiltration net-credential-use references/api.md:19

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/...
```
security skill
low Exfiltration net-credential-use references/api.md:33

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 references/api.md:47

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/blockchain/balance | jq .
```
security skill
low Exfiltration net-credential-use references/api.md:69

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 references/api.md:94

Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)
```
curl -s -u "admin:$COOKIE_PASS" \
```
security skill
low Secrets in code secret-high-entropy-token references/api.md:305

High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
```
| Diamond | `0x6a…30a` | Base (8453) |
```
table
low Secrets in code secret-high-entropy-token references/api.md:306

High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
```
| MOR Token | `0x74…8e3` | Base (8453) |
```
table
low Secrets in code secret-high-entropy-token references/economics.md:78

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
- MOR token contract: `0x74…8e3` (Base)
```
quoted
low Exfiltration net-credential-use references/troubleshooting.md:15

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 Secrets in code secret-high-entropy-token scripts/agent-registry.mjs:30

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
const IDENTITY_REGISTRY = "0x80…432";
```
quoted
low Secrets in code secret-high-entropy-token scripts/agent-registry.mjs:31

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
const REPUTATION_REGISTRY = "0x80…b63";
```
quoted
low Obfuscation obf-base64-blob scripts/bootstrap-gateway.mjs:35

Long base64-looking blob (detector / deny-list definition)
```
const COMM…B64 = 'c2st…ZDA=';
```
detector
low Secrets in code secret-high-entropy-token scripts/everclaw-wallet.mjs:30

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
const MOR_TOKEN = "0x74…8e3";
```
quoted
low Secrets in code secret-high-entropy-token scripts/everclaw-wallet.mjs:31

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
const USDC_TOKEN = "0x83…913";
```
quoted
low Secrets in code secret-high-entropy-token scripts/everclaw-wallet.mjs:33

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
const DIAMOND_CONTRACT = "0x6a…30a";
```
quoted
low Secrets in code secret-high-entropy-token scripts/everclaw-wallet.mjs:34

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
const UNISWAP_ROUTER = "0x26…481"; // Swap…r02 on Base
```
quoted
low Secrets in code secret-high-entropy-token scripts/everclaw-wallet.mjs:35

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
const UNISWAP_QUOTER = "0x3d…76a"; // QuoterV2 on Base
```
quoted
low Dangerous commands cmd-persistence scripts/gateway-guardian.sh:17

Persistence mechanism (cron / launchd / scheduled task / autorun registry) (code comment; documentation of a security skill)
```
# Install: launchd plist at ~/Library/LaunchAgents/ai.openclaw.guardian.plist
```
commentsecurity skill
low Dangerous commands cmd-pipe-to-shell scripts/gateway-guardian.sh:264

Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed; documentation of a security skill)
```
log "Executing: curl -fsSL $INSTALL_URL | bash"
```
code literalsecurity skill
low Dangerous commands cmd-pipe-to-shell-known-host scripts/install-everclaw.sh:11

Pipe-to-shell installer from a well-known host (still executes remote code) (code comment)
```
#   curl -fsSL https://raw.githubusercontent.com/profbernardoj/everclaw/main/scripts/install-everclaw.sh | bash
```
comment
low Risky intent intent-wallet-secrets scripts/install.sh:174

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
```
echo "  - Set up 1Password with your wallet private key"
```
quoted
low Exfiltration read-dotenv scripts/mor-launch-headless.sh:14

Reads a .env file (code comment)
```
# Source .env for ETH_NODE_ADDRESS and other config
```
comment
low Exfiltration read-dotenv scripts/mor-launch-headless.sh:17

Reads a .env file
```
source .env
```
low Exfiltration read-dotenv scripts/start.sh:33

Reads a .env file (code comment)
```
# Source .env
```
comment
low Risky intent intent-wallet-secrets scripts/start.sh:52

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
```
echo "🔐 Retrieving wallet private key..."
```
quoted
low Risky intent intent-wallet-secrets scripts/start.sh:73

Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
```
echo "❌ Could not retrieve wallet private key."
```
quoted
low Dangerous commands cmd-background-process scripts/start.sh:89

Starts a background / autostarted process
```
nohup ./proxy-router > "$LOG_FILE" 2>&1 &
```
low Secrets in code secret-high-entropy-token scripts/swap.sh:17

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
MOR="0x74…8e3"
```
quoted
low Secrets in code secret-high-entropy-token scripts/swap.sh:19

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
USDC="0x83…913"
```
quoted
low Secrets in code secret-high-entropy-token scripts/swap.sh:20

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
USDT="0xfd…bb2"
```
quoted
low Secrets in code secret-high-entropy-token scripts/swap.sh:23

High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
```
SWAP_ROUTER="0x26…481"
```
quoted

…and 19 more

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

Files scanned: 29. 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")
warning body-long SKILL.md body ≈ 16266 tokens (recommended < 5000); move details to references/
note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 45/100

0Inputs and preconditions. Does not say what the process needs to start
10Execution cost. Instruction body is 16266 tokens: crowds the task out of the window
20When it triggers. No condition that starts the skill
40Consistency. Frontmatter name (everclaw) differs from the folder (everclaw-inference)
50Failures and branches. 0 branches, has a failure section
60Tools and files. Uses tools (bash, web, git, python, node) that frontmatter does not declare
60Steps. 146 steps, 6 vague phrases
60Result and completion. Output format stated, no completion criterion
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 27 top-level sections: this looks like several domains in one skill
low The response is described with custom markup (10 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 1000: 120–800 characters recommended
-2localhost URLs: will not work for another user
-230 emoji in the instructions: noise for the model
-31 of 19 scripts are never mentioned in SKILL.md
+1No license
+2Single-language instructions
+4Structure: 127 headings
+3Step-by-step instructions: 146 items
+3Output format is stated explicitly
+4Has examples (66 code blocks)
+4Reference files are cited in the instructions (5 of 5)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.

Tests

— no evals.json

— no spec.yaml

— not run on models

Files · 29

CLAWHUB_WARNING.md 2K
README.md 15K
SKILL.md 68K
docs/index.html 29K
references/acquiring-mor.md 4K
references/api.md 9K
references/economics.md 6K
references/models.md 4K
references/troubleshooting.md 6K
scripts/agent-registry.mjs 13K
scripts/balance.sh 3K
scripts/bootstrap-gateway.mjs 13K
scripts/chat.sh 5K
scripts/diagnose.sh 20K
scripts/everclaw-wallet.mjs 14K
scripts/gateway-guardian.sh 20K
scripts/install-everclaw.sh 9K
scripts/install-proxy.sh 9K
scripts/install.sh 6K
scripts/mor-launch-headless.sh 2K
scripts/morpheus-proxy.mjs 16K
scripts/router.mjs 14K
scripts/session-archive.sh 7K
scripts/session.sh 5K
scripts/start.sh 4K
scripts/stop.sh 1K
scripts/swap.sh 7K
scripts/x402-client.mjs 16K
website/index.html 28K

Frontmatter

version: 0.9.7

homepage: https://everclaw.com

metadata: {"openclaw":{"emoji":"♾️","requires":{"bins":["curl","node"],"env":[{"name":"WALLET_PRIVATE_KEY","optional":true,"descri

Dates

In catalog since —

Updated in catalog 16 Jun 2026

First seen here 7 Sept 2026

Last analysis 11 Sept 2026, 17:16 UTC

Last seen in crawl 7 h ago

Score history

Date		Score	Safety	Qual.
7 Sept 2026	F	23	0	58

Similar skills

B everclaw modbender/skill-library-mcp
B everclaw ClawHub
F everclaw ClawHub