SKILLEMALL.ai
GitHub ↗ RU Sign in

CD digital-legacy

Plan what happens to your digital life if you die or become incapacitated. Inventory accounts, subscriptions, crypto wallets, important files, social media legacy contacts, and generate a sealed instruction document for trusted family. Includes encrypted digital will template and printable emergency access guide.

ClawHub Agent Skills author: voronindenis5 v0.1.2 MIT-0 11 files body ≈ 1 791 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Plan what happens to your digital life if you die or become incapacitated.

As a process D 41/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureSecuritytype 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
63/100
safety, quality, tests
Safety 60%
47
Quality 40%
88
Run on models
none yet
Process rating
D
41/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
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 · 13

    ✓ No critical or high findings

    Medium and low: 13
    • medium Risky intent intent-wallet-secrets references/account-checklist.md:52
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      | Hardware wallet     | Make/model, PIN location, seed phrase location |
    • medium Risky intent intent-wallet-secrets references/account-checklist.md:53
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      | Software wallet     | Wallet type, seed phrase location    |
    • medium Risky intent intent-wallet-secrets references/platform-policies.md:178
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      - **No platform to contact** — access is purely through seed phrase + PIN
    • medium Risky intent intent-wallet-secrets references/platform-policies.md:179
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      - If family has the seed phrase: they have full access
    • medium Risky intent intent-wallet-secrets references/platform-policies.md:181
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      - This is why documenting seed phrase location is critical
    • medium Risky intent intent-wallet-secrets references/platform-policies.md:223
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      2. **Crypto is special**: No platform to contact. Seed phrase access is
    • medium Risky intent intent-wallet-secrets references/workflow-guide.md:82
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      For each wallet, document the TYPE and ACCESS METHOD (not the seed phrase
    • medium Risky intent intent-wallet-secrets references/workflow-guide.md:88
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      # Access: seed phrase in safe deposit box, PIN written on card in safe
    • medium Risky intent intent-wallet-secrets scripts/digital_legacy.py:88
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      access_method: str = ""      # seed phrase location (NOT the phrase itself)
    • medium Risky intent intent-wallet-secrets SKILL.md:169
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      - [ ] Crypto wallets documented with access method (NOT seed phrase in plaintext)
    • low Risky intent intent-wallet-secrets references/platform-policies.md:180
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
      - If they DON'T have the seed phrase: funds are **permanently lost**
      quoted
    • low Risky intent intent-offensive-security references/security-best-practices.md:161
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - ❌ Keylogger or malware on your computer (encrypt on a clean machine if
    • low Risky intent intent-wallet-secrets scripts/digital_legacy.py:507
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
      "Access method (seed phrase LOCATION — do NOT enter the phrase itself)"
      quoted

    Files scanned: 11. 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 41/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 9 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
    • 85Steps. 61 steps, 1 vague phrases
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1791 tokens
    • 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
    • +4No input/output examples
    • +2Single-language instructions
    • +3Description length 314: enough signal without eating the budget
    • +4Structure: 16 headings
    • +3Step-by-step instructions: 61 items
    • +4Reference files are cited in the instructions (4 of 4)
    • +3All 1 scripts are documented
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.

    External checks

    ClawHub: suspicious
    The skill is coherent and not malicious, but it asks users to trust encryption for very sensitive digital-legacy data while silently falling back to a weaker homegrown cipher when the expected crypto library is unavailable.
    LLM: suspicious (high) · 14 Aug 2026