SKILLEMALL.ai
GitHub ↗ RU Sign in

FB bsc-impossible-finance

BSC (Binance Smart Chain) trading on Impossible Finance DEX — wallet creation, token swaps, pair discovery, and balance management.

Blockedguard blocked the skill: signs of malicious behaviour
ClawHub Agent Skills author: Keti Yohannes v1.0.1 2 files body ≈ 4 385 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 67/100 · Nearly there — weak spots: result and completion, when it triggers, consistency

ProcedureInfrastructuretype 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
F
34/100
safety, quality, tests
Safety 60%
10
Quality 40%
69
Run on models
none yet
Process rating
B
67/100
Nearly there
Result and completion w 14
0
When it triggers w 12
20
Consistency w 8
40
the three weakest of ten parameters · all ten
Guard blocked this skill: critical findings below. Do not install it until the author fixes them.

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Exfiltration
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. Remove the critical guard findings (secrets, dangerous commands, hidden instructions): while they stand the skill is blocked and cannot grade above F.
  2. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 6

  • critical Exfiltration exfil-send-secrets-to-url skill.md:174
    Instruction to send secrets/history to an external endpoint
    3. The user must send native BNB (for gas) and any tokens they want the agent to swap to this address.
Medium and low: 5
  • low Secrets in code secret-high-entropy-token skill.md:17
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    default: "0xCC…A33"
    quoted
  • low Secrets in code secret-high-entropy-token skill.md:21
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    default: "0xBf…E69"
    quoted
  • low Secrets in code secret-high-entropy-token skill.md:25
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    default: "0xbb…95c"
    quoted
  • low Secrets in code secret-high-entropy-token skill.md:96
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    export IF_ROUTER="0xCC…A33"
    quoted
  • low Secrets in code secret-high-entropy-token skill.md:97
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    export IF_FACTORY="0xBf…E69"
    quoted

Files scanned: 2. 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")
  • note frontmatter-key unknown frontmatter key "homepage"
  • note frontmatter-key unknown frontmatter key "env"
  • note frontmatter-key unknown frontmatter key "credentials"
  • note frontmatter-key unknown frontmatter key "dependencies"

Process rating: all ten parameters 67/100

  • 0Result and completion. Does not say what the result is
  • 20When it triggers. No condition that starts the skill
  • 40Consistency. Frontmatter name (bsc-impossible-finance) differs from the folder (impossible-finance-skill)
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Execution cost. Instruction body is 4385 tokens
  • 100Tools and files. No external tools needed
  • 100Steps. 83 steps
  • 100Failures and branches. 7 branches, has a failure section
  • 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 12 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
  • +1No license
  • +2Single-language instructions
  • +3Description length 131: enough signal without eating the budget
  • +4Structure: 44 headings
  • +3Step-by-step instructions: 83 items
  • +4Has examples (11 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.

External checks

ClawHub: clean
This is a clearly disclosed crypto trading skill that uses a dedicated local wallet and BSC network access for its stated purpose, with no evidence of hidden exfiltration or automatic unsafe behavior.
LLM: benign (high) · VirusTotal: benign · 27 May 2026