SKILLEMALL.ai
GitHub ↗ RU Sign in

BB silkyway

Agent banking and payments on Solana. Send and receive stablecoins with cancellable escrow transfers. Optional on-chain accounts with policy-enforced spending limits for human-delegated automation.

ClawHub Agent Skills author: silostack v1.0.9 28 files body ≈ 6 042 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 70/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, progress reporting

ProcedureAI 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
78/100
safety, quality, tests
Safety 60%
88
Quality 40%
64
Run on models
none yet
Process rating
B
70/100
Nearly there
Inputs and preconditions w 11
0
Progress reporting w 2
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

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 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 · 12

✓ No critical or high findings

Medium and low: 12
  • low Secrets in code secret-high-entropy-token package-lock.json:107
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…0ah+lGiA…co6+9GrJ…naQ==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:167
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…kJw+JUEz…Ry8+JzNy…KLw==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:176
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…Mvo+5lex…ani+adC5PQ==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:194
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…asG+Fkr6…2vM+P9eO…k5W+1WL8w==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:203
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha512-c/I8ZRb51j+pYGA…kSk+qT2Ea+OdWElz/OiMf…ihw==",
    detector
  • low Secrets in code secret-high-entropy-token README.md:48
    High-entropy token-like string (may be an id, hash or a credential)
    silk pay 7xKX…vNx 10 --memo "Payment for code review"
  • low Secrets in code secret-high-entropy-token README.md:51
    High-entropy token-like string (may be an id, hash or a credential)
    silk contacts add alice 7xKX…vNx
  • low Secrets in code secret-high-entropy-token SKILL.md:72
    High-entropy token-like string (may be an id, hash or a credential)
    silk pay 7xKX…vNx 10 --memo "Payment for code review"
  • low Secrets in code secret-high-entropy-token SKILL.md:107
    High-entropy token-like string (may be an id, hash or a credential)
    silk contacts add alice 7xKX…vNx
  • low Secrets in code secret-high-entropy-token SKILL.md:291
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "sender": "BrKz…sXp",
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:292
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "recipient": "7xKX…vNx",
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:316
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "transferPda": "9aE5…DJ4",
    quoted

Files scanned: 28. 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 body-long SKILL.md body ≈ 6042 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 70/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 60Result and completion. Output format stated, no completion criterion
  • 70Execution cost. Instruction body is 6042 tokens
  • 100Tools and files. No external tools needed
  • 100Steps. 24 steps
  • 100Failures and branches. 5 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 14 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (24 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)
  • +1No license
  • +2Single-language instructions
  • +3Description length 197: enough signal without eating the budget
  • +4Structure: 43 headings
  • +3Step-by-step instructions: 24 items
  • +3Output format is stated explicitly
  • +4Has examples (41 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 64.

External checks

ClawHub: suspicious
SilkyWay appears to be a real Solana payments skill, but it gives the agent real-money signing authority with plaintext local wallet keys and backend-built transactions that are signed without local verification.
LLM: suspicious (high) · VirusTotal: benign · 28 May 2026