SKILLEMALL.ai
GitHub ↗ RU Sign in

BB tradingflow

Create and manage crypto trading strategies, deploy automated trading bots, and control on-chain vaults on BSC, Aptos, and Solana. Use when the user wants to trade crypto, manage DeFi positions, set up automated strategies, check vault balances, deploy quantitative trading programs, or interact with TradingFlow platform.

ClawHub Agent Skills author: Caesar Lynch v0.0.2 MIT-0 8 files · 2 scripts body ≈ 17 556 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 79/100 · Nearly there — weak spots: execution cost

GeneratorInfrastructuretype 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%
75
Quality 40%
77
Run on models
none yet
Process rating
B
79/100
Nearly there
Execution cost w 6
10
Tools and files w 18
60
Result and completion w 14
60
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. 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 · 5

✓ No critical or high findings

Medium and low: 5
  • medium Exfiltration net-credential-use SKILL.md:901
    Credential used in a network call (verify the destination is the intended service)
    curl -X POST $BASE/claw/execute -H "Authorization: Bearer $KEY" \
  • medium Exfiltration net-credential-use SKILL.md:905
    Credential used in a network call (verify the destination is the intended service)
    curl -X POST $BASE/claw/execute -H "Authorization: Bearer $KEY" \
  • medium Exfiltration net-credential-use SKILL.md:909
    Credential used in a network call (verify the destination is the intended service)
    curl -X POST $BASE/claw/execute -H "Authorization: Bearer $KEY" \
  • medium Exfiltration net-credential-use SKILL.md:913
    Credential used in a network call (verify the destination is the intended service)
    curl -X POST $BASE/claw/execute -H "Authorization: Bearer $KEY" \
  • medium Exfiltration net-credential-use SKILL.md:917
    Credential used in a network call (verify the destination is the intended service)
    curl -X POST $BASE/claw/execute -H "Authorization: Bearer $KEY" \

Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 17556 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 79/100

  • 10Execution cost. Instruction body is 17556 tokens: crowds the task out of the window
  • 60Tools and files. Uses tools (web, python, node) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 168 steps
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 9 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 17 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)
  • -2localhost URLs: will not work for another user
  • -32 of 2 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +3Description length 322: enough signal without eating the budget
  • +4Structure: 62 headings
  • +3Step-by-step instructions: 168 items
  • +3Output format is stated explicitly
  • +4Has examples (31 code blocks)
  • +4Reference files are cited in the instructions (4 of 4)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.

External checks

ClawHub: suspicious
This appears to be a real TradingFlow crypto automation skill, but it gives an agent high-impact trading, secret, and webhook authority with controls users should review carefully.
LLM: suspicious (high) · VirusTotal: · 29 May 2026