SKILLEMALL.ai
GitHub ↗ RU Sign in

CD auto-respawn

Your agent always comes back. Anchor identity and memory on-chain so any new instance can resurrect from just an address — no local state, no single point of failure. Permanent identity and recovery on the Autonomys Network.

modbender/skill-library-mcp Agent Skills author: modbender MIT 29 files · 1 script body ≈ 4 068 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Your agent always comes back.

As a process D 47/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

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
60/100
safety, quality, tests
Safety 60%
46
Quality 40%
80
Run on models
none yet
Process rating
D
47/100
Unfinished process
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.

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

    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 · 18

    ✓ No critical or high findings

    Medium and low: 18
    • medium Risky intent intent-wallet-secrets references/auto-respawn-commands.md:13
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      Generates a new SR25519 wallet, derives the corresponding EVM address, displays the 12-word recovery phrase once, encrypts everything, and saves it locally.
    • medium Risky intent intent-wallet-secrets references/auto-respawn-commands.md:17
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      - Recovery phrase is printed to stderr — back it up immediately
    • medium Risky intent intent-wallet-secrets references/auto-respawn-commands.md:25
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      Creates a wallet from an existing recovery phrase. Derives and stores the EVM address alongside the consensus keypair.
    • medium Risky intent intent-wallet-secrets references/autonomys-network.md:31
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      Each wallet has two addresses derived from the same recovery phrase:
    • medium Risky intent intent-wallet-secrets SKILL.md:32
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      Your wallet gives you two permanent identities on the Autonomys Network: a **consensus address** (`su...`) for the base chain and an **EVM address** (`0x...`) for Auto-EVM smart contracts. Both are de
    • medium Risky intent intent-wallet-secrets SKILL.md:93
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      This generates a 12-word recovery phrase and derives both addresses:
    • medium Risky intent intent-wallet-secrets SKILL.md:97
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      ⚠️ The recovery phrase is displayed **once**. Remind the user to save it immediately.
    • medium Risky intent intent-wallet-secrets SKILL.md:197
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      Creates a new wallet with an encrypted keyfile. Derives both a consensus (`su...`) and EVM (`0x...`) address from the same mnemonic. The 12-word recovery phrase is displayed **once** — the user must b
    • medium Risky intent intent-wallet-secrets SKILL.md:205
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      Import an existing wallet from a recovery phrase. Derives and stores the EVM address.
    • low Risky intent intent-wallet-secrets auto-respawn.ts:44
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
      console.error('=== IMPORTANT: BACKUP YOUR RECOVERY PHRASE ===')
      quoted
    • low Risky intent intent-wallet-secrets auto-respawn.ts:368
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
      wallet import --name <name> --mnemonic "<words>"       Import from recovery phrase
      quoted
    • low Secrets in code secret-high-entropy-token lib/evm.ts:13
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      mainnet: '0x51…A3c',
      quoted
    • low Secrets in code secret-high-entropy-token lib/evm.ts:14
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      chronos: '0x5f…f11',
      quoted
    • low Secrets in code secret-high-entropy-token references/auto-respawn-commands.md:198
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      The MemoryChain contract address is auto-selected per network (mainnet: `0x51…A3c`, Chronos: `0x5f…f11`). If you've deployed your ow
      quoted
    • low Secrets in code secret-high-entropy-token references/autonomys-network.md:58
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - **Mainnet address**: `0x51…A3c`
      quoted
    • low Secrets in code secret-high-entropy-token references/autonomys-network.md:59
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - **Chronos address**: `0x5f…f11`
      quoted
    • low Secrets in code secret-high-entropy-token SKILL.md:184
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - **Chronos:** `0x5f…f11`
      quoted
    • low Secrets in code secret-high-entropy-token SKILL.md:185
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - **Mainnet:** `0x51…A3c`
      quoted

    Files scanned: 20. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 47/100

    • 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
    • 30Running it twice. 22 mutating operations with no state check
    • 55Failures and branches. 1 branches
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 70Execution cost. Instruction body is 4068 tokens
    • 85Steps. 52 steps, 1 vague phrases
    • 100Consistency. Name and required fields are in place
    • 100Progress reporting. Reports progress
    • low The response is described with custom markup (6 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)
    • +3Output format is not stated: the model decides each time
    • -42 reference files, but SKILL.md never points to them: the model will not open them
    • +1No license
    • +2Single-language instructions
    • +3Description length 224: enough signal without eating the budget
    • +4Structure: 34 headings
    • +3Step-by-step instructions: 52 items
    • +4Has examples (19 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.