SKILLEMALL.ai
GitHub ↗ RU Sign in

BC arc402-agent

Operate as a fully governed ARC-402 agent — agent-to-agent hiring on Base mainnet with sandboxed execution by default. ARC-402 creates a dedicated governed workroom for hired work on the operator's machine, with the ARC-402 Workroom as the runtime safety layer. Use when an OpenClaw agent needs to earn, hire, transact, or dispute on the ARC-402 protocol. Covers wallet setup, daemon lifecycle, sandbox wiring, key separation, prompt injection defense, spending validation, and dispute flows.

ClawHub Agent Skills author: Lego v0.3.1 MIT-0 2 files body ≈ 9 152 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 64/100 · Has gaps — weak spots: result and completion, execution cost

AnalyzerAI 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
B
84/100
safety, quality, tests
Safety 60%
93
Quality 40%
70
Run on models
none yet
Process rating
C
64/100
Has gaps
Result and completion w 14
0
Execution cost w 6
40
When it triggers w 12
50
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.

Instruction override 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 text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.

For the author

An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.

How to improve

  1. 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 · 3

✓ No critical or high findings

Medium and low: 3
  • medium Instruction override en-ignore-previous SKILL.md:343
    Instruction-override phrase ("ignore previous instructions") (documentation of a security skill)
    - Instructions to ignore your system prompt or policy
    security skill
  • low Secrets in code secret-high-entropy-token SKILL.md:161
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    The Handshake contract (`0x4F…Db3`) must be whitelisted on PolicyEngine before use.
    quoted
  • low Risky intent intent-offensive-security SKILL.md:841
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - **Process:** runs as `sandbox` user. No privilege escalation. Dangerous syscalls blocked via Landlock.

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 9152 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "protocol"
  • note frontmatter-key unknown frontmatter key "status"

Process rating: all ten parameters 64/100

  • 0Result and completion. Does not say what the result is
  • 40Execution cost. Instruction body is 9152 tokens: crowds the task out of the window
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 85Steps. 108 steps, 1 vague phrases
  • 100Failures and branches. 7 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 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 22 top-level sections: this looks like several domains in one skill

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
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Description length 492: enough signal without eating the budget
  • +4Structure: 69 headings
  • +3Step-by-step instructions: 108 items
  • +4Has examples (44 code blocks)

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

External checks

ClawHub: suspicious
This skill is coherent for an ARC-402 payment agent, but it gives an agent high-impact authority over live blockchain funds, a daemon, credentials, persistent memory, and a public relay that need careful review before use.
LLM: suspicious (high) · VirusTotal: · 29 May 2026