SKILLEMALL.ai
RU Sign in

BB claws-temple-bounty

Use when the user is explicitly inside the Claws Temple Bounty 2.0 workflow, names Claws Temple / 龙虾圣殿 / Claws Temple Bounty 2.0, or is already continuing this branded five-task path. This skill packages the five-step journey that sends an Agent into the wild to make friends. Do not use for generic numbered tasks, generic bounty requests, or unrelated partner-matching requests outside this brand context.

ClawHub Agent Skills author: hzz780 v0.2.17 MIT-0 37 files · 5 scripts body ≈ 4 488 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process B 66/100 · Nearly there — weak spots: result and completion, consistency, running it twice

ProcedureMarketingAI and agentsInfrastructuretype 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
76/100
safety, quality, tests
Safety 60%
70
Quality 40%
85
Run on models
none yet
Process rating
B
66/100
Nearly there
Result and completion w 14
0
Running it twice w 4
30
Consistency w 8
40
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 · 10

    ✓ No critical or high findings

    Medium and low: 10
    • medium Risky intent intent-wallet-secrets references/output-contract.md:225
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      - if the `CA` signer exists but the keystore password is missing, ask the user for that password only once and then continue automatically
    • medium Risky intent intent-wallet-secrets references/task-flows/task-3-faction-oath.md:33
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      8. If the `CA` signer exists but the keystore password is missing, ask the user for the `CA keystore` password only once and then continue automatically.
    • medium Risky intent intent-wallet-secrets references/task-flows/task-3-faction-oath.md:76
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      - password request wording when the `CA` keystore password is missing
    • medium Risky intent intent-wallet-secrets skill-card.md:22
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      Risk: The skill may ask for a CA keystore password. <br>
    • medium Risky intent intent-wallet-secrets SKILL.md:98
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      - for Task 3, if the `CA` context is present but the keystore password is not yet available, ask the user for the `CA keystore` password only once and then continue automatically
    • low Risky intent intent-wallet-secrets references/clawhub-runtime-notes.md:9
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
      - Task 3 may ask for the `CA keystore password` once when a real write needs the active `CA` context.
      quoted
    • low Risky intent intent-wallet-secrets references/examples/task-3-faction-oath.en.md:61
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (test fixture / example file)
      If the current `CA` context is already available but the keystore password is still missing, the reply should say:
      fixture
    • low Risky intent intent-wallet-secrets references/examples/task-3-faction-oath.en.md:63
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (test fixture / example file; quoted — discussed, not commanded)
      `I have already confirmed that your current identity entry can continue this faction oath, but this step still needs the CA keystore password once. After you provide it, I will continue the authorizat
      fixturequoted
    • low Risky intent intent-wallet-secrets scripts/validate_clawhub_bundle.py:116
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
      "CA keystore password",
      quoted
    • low Risky intent intent-wallet-secrets SKILL.md:227
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
      - Task 3 may ask for the `CA keystore password` once when a real write needs the active `CA` context.
      quoted

    Files scanned: 37. 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 66/100

    • 0Result and completion. Does not say what the result is
    • 30Running it twice. 21 mutating operations with no state check
    • 40Consistency. Frontmatter name (claws-temple-bounty) differs from the folder (claws-temple-bounty-v2)
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 70Execution cost. Instruction body is 4488 tokens
    • 100Steps. 130 steps
    • 100When it triggers. States when to use and when not to
    • 100Failures and branches. 8 branches, has a failure section
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 11 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
    • +3Output format is not stated: the model decides each time
    • +4No input/output examples
    • -35 of 6 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +4Description says when NOT to use the skill
    • +3Description length 407: enough signal without eating the budget
    • +4Structure: 18 headings
    • +3Step-by-step instructions: 130 items
    • +4Reference files are cited in the instructions (3 of 5)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.

    External checks

    ClawHub: suspicious
    This skill is a branded bounty helper, but it can install dependencies and drive account, token-approval, DAO-vote, and public-platform actions with inadequate user-facing disclosure.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026