SKILLEMALL.ai
RU Sign in

BF harvest-rewards

Harvest pending CAKE and partner-token rewards from PancakeSwap farming positions. Use when user says "/harvest-rewards", "harvest all my pending CAKE rewards", "how much do I have to claim from my farms", "claim my Syrup Pool rewards", "pending farming rewards", "collect CAKE rewards", or asks what they can harvest.

ClawHub Agent Skills author: pcs-bot v1.0.0 MIT-0 5 files body ≈ 3 708 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process F 48/100 · Will not run — References files that are not bundled: references/fetch-solana.cjs

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
B
84/100
safety, quality, tests
Safety 60%
83
Quality 40%
85
Run on models
none yet
Process rating
F
48/100
Will not run
References files that are not bundled: references/fetch-solana.cjs
Tools and files w 18
0
Inputs and preconditions w 11
0
Progress reporting w 2
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.

Broad scope 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 skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. 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 · 13

✓ No critical or high findings

Medium and low: 13
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash(curl:*)
    allowed-tools: Read Write Edit Glob Grep Bash(curl:*) Bash(jq:*) Bash(python3:*) Bash(node:*) WebFetch WebSearch Task(subagent_type:Explore) AskUserQuestion
  • low Secrets in code secret-high-entropy-token references/fetch-infinity-pending.py:17
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    56:   '0xEA…877',
    quoted
  • low Secrets in code secret-high-entropy-token references/fetch-infinity-pending.py:18
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    8453: '0xEA…877',
    quoted
  • low Secrets in code secret-high-entropy-token references/fetch-v3-pending.py:15
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    'bsc':     ('https://bsc-rpc.publicnode.com',          '0x55…59e'),
    quoted
  • low Secrets in code secret-high-entropy-token references/fetch-v3-pending.py:16
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    'eth':     ('https://ethereum-rpc.publicnode.com',     '0x55…59e'),
    quoted
  • low Secrets in code secret-high-entropy-token references/fetch-v3-pending.py:17
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    'arbitrum':('https://arb1….io/rpc',            '0x5e…694'),
    quoted
  • low Secrets in code secret-high-entropy-token references/fetch-v3-pending.py:18
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    'base':    ('https://mainnet.base.org',                '0xC6…5A3'),
    detector
  • low Secrets in code secret-high-entropy-token references/fetch-v3-pending.py:19
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    'zksync':  ('https://mainnet.era.zksync.io',           '0x4c…463'),
    detector
  • low Secrets in code secret-high-entropy-token SKILL.md:126
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | MasterChef v2      | `0xa5…652` | V2 LP farm staking & CAKE rewards (BSC only) |
    table
  • low Secrets in code secret-high-entropy-token SKILL.md:128
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | CAKE Token         | `0x0E…E82` | CAKE ERC-20 token                            |
    table
  • low Secrets in code secret-high-entropy-token SKILL.md:129
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | PositionManager v3 | `0x46…364` | V3 NFT position manager                      |
    table
  • low Secrets in code secret-high-entropy-token SKILL.md:135
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | BSC / ETH | `0x55…59e` |
    table
  • low Secrets in code secret-high-entropy-token SKILL.md:136
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | Arbitrum  | `0x5e…694` |
    table

Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: references/fetch-solana.cjs
  • note frontmatter-key unknown frontmatter key "slug"
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 48/100

Will not run. References files that are not bundled: references/fetch-solana.cjs
  • 0Tools and files. 1 referenced file(s) missing: references/fetch-solana.cjs
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 40Consistency. Frontmatter name (harvest-rewards) differs from the folder (pcs-harvest-rewards)
  • 50When it triggers. No condition that starts the skill
  • 55Failures and branches. 1 branches
  • 60Result and completion. Output format stated, no completion criterion
  • 100Steps. 12 steps
  • 100Execution cost. Instruction body is 3708 tokens
  • 100Running it twice. No mutating operations
  • 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

  • +4Description does not say when NOT to use the skill (false activations)
  • +2Single-language instructions
  • +5Description quotes 6 example trigger phrases
  • +3Description length 318: enough signal without eating the budget
  • +4Structure: 22 headings
  • +3Step-by-step instructions: 12 items
  • +3Output format is stated explicitly
  • +4Has examples (16 code blocks)
  • +1License stated

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

External checks

ClawHub: suspicious
This is mostly a read-only PancakeSwap rewards checker, but it has review-worthy issues: silent dependency installation, unnecessary system-metadata pinging, and broader tool authority than the workflow needs.
LLM: suspicious (high) · VirusTotal: · 29 May 2026