Closed envelope pipeline
Leibniz Layer™
01 — input
Prompt Firewall
Blocks jailbreaks, DAN/STAN, drain-wallet injections before they reach the LLM.
COMMIT / BLOCK
02 — guard
Wallet Guardian
Masks seed phrases, private keys, and addresses. Zero PII reaches the model.
COMMIT / REDACT
03 — comply
MEV Compliance
Front-running, wash trading, KYC/AML flags. EU AI Act Art. 9/13 aligned.
COMMIT / BLOCK
04 — verify
Semantic Drift
Guards market signals against hallucination. Fabricated prices → HALLUCINATION_DRIFT.
IN_COMMIT / DRIFT
05 — sanitize
Output Sanitizer
Last sweep: strips API keys, connection strings, shell injection from model output.
COMMIT / REDACT
06 — commit
Crypto Commit
Final seal. tx_hash + chain_hash on-chain. Merkle proof. Regulator-ready export.
ON-CHAIN
8 modular skills
Verified · Live · Free to download
Verified ✓
DCL Prompt Firewall Crypto
/dcl-prompt-firewall-crypto
First gate for every crypto agent. Blocks jailbreaks, DAN/STAN, role-switch, drain-wallet injections, and unlimited-approval attacks.
Verified ✓
DCL Wallet Guardian
/dcl-wallet-guardian
Masks seed phrases, private keys, and wallet addresses before they reach any LLM context. Auto-redacts BIP-39 mnemonics, WIF keys, ETH private keys.
Verified ✓
DCL Trade Verifier
/dcl-trade-verifier
Audits every AI trading decision. Blocks guaranteed-return claims and unqualified advice. Generates immutable receipts with tx_hash for compliance.
Verified ✓
DCL MEV Compliance Shield
/dcl-mev-compliance
Detects front-running, sandwich attacks, wash trading, and KYC/AML red flags. EU AI Act Art. 9/13 aligned. For institutional DeFi desks and RWA platforms.
Verified ✓
DCL Provenance Tracker Crypto
/dcl-provenance-tracker-crypto
Supply chain verification for on-chain skills and smart contracts. Detects eval/exec obfuscation, selfdestruct, delegatecall, credential exfiltration.
Verified ✓
DCL Semantic Drift Crypto
/dcl-semantic-drift-crypto
Guards market signals against hallucination. Detects fabricated prices, invented token names, contradicted indicators. Verdict: IN_COMMIT or HALLUCINATION_DRIFT.
Verified ✓
DCL Output Sanitizer
/dcl-output-sanitizer
Last gate before delivery. Strips API keys, connection strings, shell injection fragments, and toxic content reproduced from tools or RAG context.
Verified ✓
DCL Crypto Commit
/dcl-crypto-commit
Commits every trading decision to the Leibniz Layer™ audit chain. Returns tx_hash + chain_hash as tamper-evident Merkle proof. The final seal on every DeFi agent action.
Quick start
Any HTTP client
evaluate.sh — call any DCL policy
# Gate 1 — block malicious prompts curl -s -X POST https://webhook.fronesislabs.com/evaluate \ -H "Content-Type: application/json" \ -d '{"response": "<user prompt>", "policy": "prompt_firewall_crypto"}' # Gate 2 — audit trade decision curl -s -X POST https://webhook.fronesislabs.com/evaluate \ -d '{"response": "<trade signal>", "policy": "trade_verifier"}' # Returns for every call: { "verdict": "COMMIT", "tx_hash": "a3f8c2e1d09b4f76...", "chain_hash": "7c4d9a0e2f31b85a...", "chain_depth": 4821, "powered_by": "Leibniz Layer™ | Fronesis Labs" }
Pricing
Free to institutional
Core
Free
forever · no account needed
All 8 skills, all 14 policies
- Public audit chain
- 100 evaluations / day
- tx_hash + chain_hash proofs
- Download all SKILL.md files
- ClawHub compatible
Leibniz Crypto
$79
per year · unlimited evaluations
For protocol teams & signal providers
- Everything in Core
- Private audit chain
- Multi-LLM consensus mode
- Offline DCL Evaluator
- Regulator PDF export
- Priority support
Institutional
x402
per commit · Base Mainnet · USDC
For Binance AI Skills, BankrBot, RWA
- On-chain commit proofs
- ERC-8004 agent identity
- SLA + dedicated infra
- Custom policy rules
- MiFID II / FCA / SEC export