SKILLEMALL.ai
GitHub ↗ RU Sign in

CF flapskill

创建 V5 代币（0 税或税收，四档分配）；USDT 买入、按数量或按比例卖出；做市刷量（每轮 5 买 5 卖，启动销毁 5 万枚，无 USDT 时卖回 funder 后继续，日志北京时间）。说「蝴蝶技能」触发。依赖 BNB Chain MCP。

LeoYeAI/openclaw-master-skills Agent Skills author: LeoYeAI MIT 13 files body ≈ 4 295 tokens Open the sourcegithub.com↗ analyzed 2 d ago

创建 V5 代币（0 税或税收，四档分配）；USDT 买入、按数量或按比例卖出；做市刷量（每轮 5 买 5 卖，启动销毁 5 万枚，无 USDT 时卖回 funder 后继续，日志北京时间）。说「蝴蝶技能」触发。依赖 BNB Chain MCP。

As a process F 26/100 · Will not run — References files that are not bundled: ../../scripts/README.md

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
74/100
safety, quality, tests
Safety 60%
79
Quality 40%
66
Run on models
none yet
Process rating
F
26/100
Will not run
References files that are not bundled: ../../scripts/README.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
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.

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The text references files that are not there: add them or drop the references.
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 · 17

✓ No critical or high findings

Medium and low: 17
  • medium Exfiltration exfil-send-secrets-to-url scripts/upload-token-meta.js:94
    Instruction to send secrets/history to an external endpoint (security demo / example; quoted — discussed, not commanded)
    console.error("示例: node upload-token-meta.js ./logo.png \"代币简介\" \"https://example.com\"");
    demoquoted
  • low Secrets in code secret-high-entropy-token package-lock.json:25
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…p81+8Ob3…L40/b0i7…gQw==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:87
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha512-+lF0B…kdX+94aG…d8c+B3KT…U6A==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:121
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…9dM/mwVgvbZJaSNaRk+bshk…Kbz+IoId…W0Q==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:151
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…SDq+2kAA…MOe/+5cdoEdg==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:186
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…FrF+LTRo…W3g==",
    detector
  • low Secrets in code secret-high-entropy-token README.md:122
    High-entropy token-like string (may be an id, hash or a credential)
    税收地址：0x62…199
  • low Secrets in code secret-high-entropy-token README.md:152
    High-entropy token-like string (may be an id, hash or a credential)
    使用蝴蝶技能对 0xe1…777 进行做市刷量，随机范围：1-10U，资金归集地址：0x62…199
  • low Secrets in code secret-high-entropy-token README.md:169
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    **捐款地址**：`0x62…199`
    quoted
  • low Secrets in code secret-high-entropy-token references/contract-abi.md:4
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    **USDT（BSC）**：`0x55…955`。
    quoted
  • low Secrets in code secret-high-entropy-token scripts/find-vanity-salt.js:16
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const PORTAL_BSC = "0xe2…De0";
    quoted
  • low Secrets in code secret-high-entropy-token scripts/find-vanity-salt.js:18
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const TAX_…BSC = "0x29…aA8";
    quoted
  • low Secrets in code secret-high-entropy-token scripts/find-vanity-salt.js:19
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const TAX_…BSC = "0xae…7BA";
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:12
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    **USDT 合约地址（BSC）**：`0x55…955`。
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:82
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | `tokenAddress` | USDT：`0x55…955` |
    table
  • low Secrets in code secret-high-entropy-token SKILL.md:171
    High-entropy token-like string (may be an id, hash or a credential)
    使用蝴蝶技能对 0xe1…777 进行做市刷量，随机范围：1-10U，资金归集地址：0x62…199
  • low Secrets in code secret-high-entropy-token SKILL.md:245
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - ① **approve_token_spending**：token=USDT（`0x55…955`），spender=FlapSkill（`0x48…edc`），amount=**无限授权** max uint256：`"115792089237316195
    quoted

Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: ../../scripts/README.md
  • note frontmatter-key unknown frontmatter key "displayName"

Process rating: all ten parameters 26/100

Will not run. References files that are not bundled: ../../scripts/README.md
  • 0Tools and files. 1 referenced file(s) missing: ../../scripts/README.md
  • 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. 16 mutating operations with no state check
  • 40Consistency. Frontmatter name (flapskill) differs from the folder (flap-skills)
  • 70Execution cost. Instruction body is 4295 tokens
  • 100Steps. 49 steps
  • 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
  • -32 of 6 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 123: enough signal without eating the budget
  • +4Structure: 27 headings
  • +3Step-by-step instructions: 49 items
  • +4Has examples (2 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.