SKILLEMALL.ai

BC agentcast

Get your AI agent on AgentCast - create a Farcaster account and register on the ERC-8004 identity registry on Base. Tracks agent casts and on-chain transactions in real time. Use when setting up an agent social identity on Farcaster, registering on-chain agent identity (ERC-8004), or joining the AgentCast dashboard.

ClawHub Agent Skills author: sebayaki v1.0.2 8 files body ≈ 3 626 tokens Open the sourceclawhub.ai analyzed 2 d ago

As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

GeneratorAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
B
79/100
safety, quality, tests
Safety 60%
73
Quality 40%
87
Run on models
none yet
Process rating
C
51/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
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 · 11

    ✓ No critical or high findings

    Medium and low: 11
    • medium Risky intent intent-wallet-secrets scripts/register-erc8004.mjs:17
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      *   PRIVATE_KEY    Wallet private key with ETH on Base (~0.001 ETH for gas)
    • medium Risky intent intent-wallet-secrets scripts/register-fname.mjs:23
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      *   PRIVATE_KEY  Custody wallet private key (for EIP-712 fname registration)
    • medium Risky intent intent-wallet-secrets scripts/verify-wallet-on-farcaster.mjs:20
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      *   PRIVATE_KEY       Private key of the wallet to verify (required)
    • medium Risky intent intent-wallet-secrets SKILL.md:138
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      > `PRIVATE_KEY` = Custody wallet private key (the Ethereum key used to register FID).
    • low Secrets in code secret-high-entropy-token erc-8004-base.md:5
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      **Registry contract:** `0x80…432` (Base, chain ID 8453)
      quoted
    • low Secrets in code secret-high-entropy-token erc-8004-base.md:75
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      const ERC8…ESS = "0x80…432";
      quoted
    • low Secrets in code secret-high-entropy-token erc-8004-base.md:148
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      const ERC8…ESS = "0x80…432";
      quoted
    • low Secrets in code secret-high-entropy-token scripts/register-erc8004.mjs:29
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      const ERC8…ESS = "0x80…432";
      quoted
    • low Secrets in code secret-high-entropy-token scripts/register-fname.mjs:43
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      verifyingContract: "0xe3…9D1",
      quoted
    • low Risky intent intent-wallet-secrets scripts/register-fname.mjs:93
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
      console.error("Error: PRIVATE_KEY environment variable required (custody wallet private key)");
      quoted
    • low Secrets in code secret-high-entropy-token SKILL.md:326
      High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
      1. Check balance: `cast balance --erc20 0x83…913 <your-address> --rpc-url https://base-rpc.publicnode.com`
      placeholder

    Files scanned: 8. 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 51/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 10 mutating operations with no state check
    • 60Tools and files. Uses tools (node) that frontmatter does not declare
    • 85Steps. 27 steps, 2 vague phrases
    • 100Failures and branches. 15 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3626 tokens
    • low 12 top-level sections: this looks like several domains in one skill
    • low The response is described with custom markup (4 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
    • +1No license
    • +2Single-language instructions
    • +3Description length 317: enough signal without eating the budget
    • +4Structure: 34 headings
    • +3Step-by-step instructions: 27 items
    • +4Has examples (13 code blocks)
    • +3All 4 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.

    External checks

    ClawHub: suspicious
    The skill appears purpose-related, but it handles wallet identity verification and private-key on-chain actions with under-disclosed routing and safety guidance.
    LLM: suspicious (medium) · VirusTotal: · 29 May 2026