SKILLEMALL.ai
GitHub ↗ RU Sign in

CC karmabank

AI agents borrow USDC based on their Moltbook karma score. Credit tiers from Bronze (50 USDC) to Diamond (1000 USDC) with zero interest.

ClawHub Agent Skills author: abdhilabs v1.0.0 58 files · 1 script body ≈ 3 065 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, consistency

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
C
72/100
safety, quality, tests
Safety 60%
74
Quality 40%
69
Run on models
none yet
Process rating
C
51/100
Has gaps
Result and completion w 14
0
Progress reporting w 2
0
When it triggers w 12
20
the three weakest of ten parameters · all ten
This is a copy of a skill from another catalog; the rating counts the canonical one: karmabank (ClawHub)

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.
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 · 14

✓ No critical or high findings

Medium and low: 14
  • medium Exfiltration net-redirectable-api-key scripts/circle-entity-secret.js:11
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • medium Exfiltration net-redirectable-api-key scripts/circle-entity-secret.ts:19
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • medium Exfiltration net-credential-use TODO.md:142
    Credential used in a network call (verify the destination is the intended service)
    curl -H "Authorization: Bearer $MOLTBOOK_API_KEY" \
  • low Secrets in code secret-high-entropy-token package-lock.json:311
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "integrity": "sha5…ywo+qwL+oL8H…C1U+vRfLQDvw==",
    quoted
  • low Secrets in code secret-high-entropy-token package-lock.json:327
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha512-Yqfm+XDx0+Prh3…1yC+JWZ2…IL7+vK+Clp7…D7g==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:340
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…xZl+RoGR…fbT/ZgrF…0EA==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:353
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…3bJ+V0If…IXN+CL65…a4w==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:369
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "integrity": "sha5…H47+FFon…OsV/4+RRsz…0ig==",
    quoted
  • low Obfuscation obf-base64-blob scripts/create-with-ciphertext.js:7
    Long base64-looking blob (quoted — discussed, not commanded)
    const CIPHERTEXT = process.env.CIRCLE_CIPHERTEXT || `PQ5iqmm/skPx…GtU+vmgN…eZT+G+PXGb…FSV/Yfma…ugE
    quoted
  • low Secrets in code secret-high-entropy-token src/adapters/circle.test.ts:77
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    '0x74…4e0',
    fixturequoted
  • low Secrets in code secret-high-entropy-token src/adapters/circle.test.ts:98
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    '0x74…4e0',
    fixturequoted
  • low Secrets in code secret-high-entropy-token src/adapters/circle.test.ts:109
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    '0x74…4e0',
    fixturequoted
  • low Secrets in code secret-high-entropy-token src/adapters/circle.ts:39
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    address: '0x74…4e0',
    quoted
  • low Secrets in code secret-high-entropy-token TODO.md:269
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - **Key:** `molt…nnI`
    quoted

Files scanned: 56. 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")

Process rating: all ten parameters 51/100

  • 0Result and completion. Does not say what the result is
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 7 mutating operations with no state check
  • 40Consistency. Frontmatter name (karmabank) differs from the folder (agent-credit-system)
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 51 steps
  • 100Execution cost. Instruction body is 3065 tokens
  • low 15 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (7 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
  • -315 of 15 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 136: enough signal without eating the budget
  • +4Structure: 48 headings
  • +3Step-by-step instructions: 51 items
  • +4Has examples (40 code blocks)

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

External checks

ClawHub: suspicious
KarmaBank is a coherent USDC lending skill, but its financial and credential handling has serious review-worthy safety gaps before installation.
LLM: suspicious (high) · VirusTotal: suspicious · 10 Sept 2026