SKILLEMALL.ai

CF agentic-lending-morpho

Plan and execute the Morpho-first agentic lending workflow for Api3-backed markets. Use when a user wants a Morpho market or market set for selected collateral and borrow assets, needs the oracle route resolved for those assets, wants Api3 feed readiness checked or funded when safe, and then wants the Morpho oracle + market deployment and verification path run honestly. This variant can progress from planning into real feed funding and market deployment when the supported path is available and the user explicitly allows signer-backed execution. Default to planning, dry-run, or guarded verification first. Do not use for Euler EVK flows or unsupported oracle routes.

ClawHub Agent Skills author: dave v0.1.11 MIT-0 46 files body ≈ 3 204 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process F 60/100 · Will not run — References files that are not bundled: references/deployment-packs/<chain>/

ProcedureInfrastructureAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
C
74/100
safety, quality, tests
Safety 60%
66
Quality 40%
85
Run on models
none yet
Process rating
F
60/100
Will not run
References files that are not bundled: references/deployment-packs/<chain>/
Tools and files w 18
0
Progress reporting w 2
0
Running it twice w 4
30
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 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 · 30

✓ No critical or high findings

Medium and low: 30
  • medium Exfiltration net-credential-use scripts/lib/part2-morpho-planner.js:1008
    Credential used in a network call (verify the destination is the intended service)
    assertHexAddressIfPresent(entry.irmAddress, `${label}.byMarketKey.${marketKey}.irmAddress`);
  • low Secrets in code secret-high-entropy-token data/part2/contract-artifacts/Api3PartialAggregatorV2V3Interface.json:2
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "contractName": "Api3…ace",
    quoted
  • low Secrets in code secret-high-entropy-token data/part2/evk-addresses.api3-supported-overlap.json:14
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "evc": "0x0C…383",
    quoted
  • low Secrets in code secret-high-entropy-token data/part2/evk-addresses.api3-supported-overlap.json:15
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "eVaultFactory": "0x29…C8e"
    quoted
  • low Secrets in code secret-high-entropy-token data/part2/evk-addresses.api3-supported-overlap.json:18
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "edgeFactory": "0xA9…9Bd",
    quoted
  • low Secrets in code secret-high-entropy-token data/part2/evk-addresses.api3-supported-overlap.json:19
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "evkFactoryPerspective": "0xB3…182",
    quoted
  • low Secrets in code secret-high-entropy-token data/part2/evk-addresses.api3-supported-overlap.json:20
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "escrowedCollateralPerspective": "0x4e…DdE"
    quoted
  • low Secrets in code secret-high-entropy-token data/part2/feed-status.json:7
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "supp…ace": true,
    quoted
  • low Secrets in code secret-high-entropy-token data/part2/feed-status.json:19
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "supp…ace": true,
    quoted
  • low Secrets in code secret-high-entropy-token data/part2/feed-status.json:31
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "supp…ace": true,
    quoted
  • low Secrets in code secret-high-entropy-token data/part2/feed-status.json:43
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "supp…ace": true,
    quoted
  • low Secrets in code secret-high-entropy-token data/part2/feed-status.json:57
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "supp…ace": true,
    quoted
  • low Secrets in code secret-high-entropy-token references/example-request.json:16
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    "address": "0xaf…831"
    fixturequoted
  • low Secrets in code secret-high-entropy-token references/live-request-template.json:16
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "address": "0xaf…831"
    quoted
  • low Secrets in code secret-high-entropy-token scripts/lib/api3-feed-manager.js:16
    High-entropy token-like string (may be an id, hash or a credential)
    Api3…ory,
  • low Secrets in code secret-high-entropy-token scripts/lib/api3-feed-manager.js:18
    High-entropy token-like string (may be an id, hash or a credential)
    comp…ess,
  • low Secrets in code secret-high-entropy-token scripts/lib/api3-feed-manager.js:961
    High-entropy token-like string (may be an id, hash or a credential)
    const communalProxy = chainState?.communalProxy || comp…ess(chainId, dapiName);
  • low Secrets in code secret-high-entropy-token scripts/lib/api3-feed-manager.js:1045
    High-entropy token-like string (may be an id, hash or a credential)
    const communalProxy = chainState?.communalProxy || comp…ess(chainId, dapiName);
  • low Secrets in code secret-high-entropy-token scripts/lib/api3-feed-manager.js:1496
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    from: '0x00…EaD',
    quoted
  • low Secrets in code secret-high-entropy-token scripts/lib/part2-morpho-planner.js:13
    High-entropy token-like string (may be an id, hash or a credential)
    const { Api3…ory } = require('@api3/contracts');
  • low Secrets in code secret-high-entropy-token scripts/lib/part2-morpho-planner.js:53
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const DEFAULT_DRY_RUN_SIMULATION_FROM_ADDRESS = '0x00…EaD';
    quoted
  • low Exfiltration net-credential-use scripts/lib/part2-morpho-planner.js:1007
    Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)
    assertAllowedKeys(entry, ['irmAddress', 'lltv'], `${label}.byMarketKey.${marketKey}`);
    quoted
  • low Exfiltration net-credential-use scripts/lib/part2-morpho-planner.js:1913
    Credential used in a network call (verify the destination is the intended service) (detector / deny-list definition)
    blockers.push(`No approved Morpho IRM is configured for ${marketKey}. Supply request.morphoPolicy.defaultIrmAddress or request.morphoPolicy.byMarketKey.${marketKey}.irmAddress.`);
    detector
  • low Secrets in code secret-high-entropy-token scripts/lib/part2-morpho-planner.js:2289
    High-entropy token-like string (may be an id, hash or a credential)
    function buil…ion(proxyDeployment, marketKeys = []) {
  • low Secrets in code secret-high-entropy-token scripts/lib/part2-morpho-planner.js:2335
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    return buil…ion(proxyDeployment, [...marketKeys].sort());
    placeholder
  • low Secrets in code secret-high-entropy-token scripts/lib/part2-planner.js:22
    High-entropy token-like string (may be an id, hash or a credential)
    Api3…ce: path.join(CONTRACT_ARTIFACT_DIR, 'Api3PartialAggregatorV2V3Interface.json'),
  • low Secrets in code secret-high-entropy-token scripts/lib/part2-planner.js:165
    High-entropy token-like string (may be an id, hash or a credential)
    supp…ce: classification !== 'unsupported',
  • low Secrets in code secret-high-entropy-token scripts/lib/part2-planner.js:1597
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    'Api3…ace remains the preferred compatibility layer for Api3-backed legs.',
    quoted
  • low Secrets in code secret-high-entropy-token scripts/lib/part2-planner.js:1609
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    'Api3 via Api3…ace is the default route when a direct compatible feed is sufficient.',
    quoted
  • low Secrets in code secret-high-entropy-token scripts/lib/part2-planner.js:1735
    High-entropy token-like string (may be an id, hash or a credential)
    supp…ce: true,

Files scanned: 46. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: references/deployment-packs/<chain>/

Process rating: all ten parameters 60/100

Will not run. References files that are not bundled: references/deployment-packs/<chain>/
  • 0Tools and files. 1 referenced file(s) missing: references/deployment-packs/<chain>/
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 60 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 60Result and completion. Output format stated, no completion criterion
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 85Steps. 97 steps, 1 vague phrases
  • 100Failures and branches. 11 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3204 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 11 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (6 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
  • +4No input/output examples
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 672: enough signal without eating the budget
  • +4Structure: 12 headings
  • +3Step-by-step instructions: 97 items
  • +3Output format is stated explicitly
  • +4Reference files are cited in the instructions (5 of 5)

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

External checks

ClawHub: suspicious
This skill openly supports on-chain financial actions, but it also exposes broader EVK tooling and can persist raw signing keys if users provide them.
LLM: suspicious (high) · VirusTotal: · 15 Jun 2026