Ethicore Engine™ — Guardian SDK

Name: Ethicore Engine™ — Guardian SDK
Author: Oracles Technologies LLC

AgentA2A

by Oracles Technologies LLChomepage ↗v2.7.0

Is this yours?

This record is unclaimed

Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.

Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"ethicore-enginetm-guardian-sdk","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.

Claim this record

Observed by Wellknown

Evidence

Everything here was measured by our prober or read from a registry. Nothing is self-reported.

30-day availability66/66 checks ok

Endpoints

https://oraclestechnologies.com/guardiana2a · auth: none · checked on a schedule

Registry facts

Not distributed through a package registry we index.

when	check	result	http	latency	detail
5 h ago	a2a card	ok	200	85 ms	card: Ethicore Engine™ — Guardian SDK · 7 skills
12 h ago	a2a card	ok	200	22 ms	card: Ethicore Engine™ — Guardian SDK · 7 skills
19 h ago	a2a card	ok	200	28 ms	card: Ethicore Engine™ — Guardian SDK · 7 skills
26 h ago	a2a card	ok	200	66 ms	card: Ethicore Engine™ — Guardian SDK · 7 skills
32 h ago	a2a card	ok	200	27 ms	card: Ethicore Engine™ — Guardian SDK · 7 skills
2 d ago	a2a card	ok	200	24 ms	card: Ethicore Engine™ — Guardian SDK · 7 skills
2 d ago	a2a card	ok	200	79 ms	card: Ethicore Engine™ — Guardian SDK · 7 skills
2 d ago	a2a card	ok	200	50 ms	card: Ethicore Engine™ — Guardian SDK · 7 skills
2 d ago	a2a card	ok	200	65 ms	card: Ethicore Engine™ — Guardian SDK · 7 skills
3 d ago	a2a card	ok	200	24 ms	card: Ethicore Engine™ — Guardian SDK · 7 skills

Declared by sources

What the publisher says

Attributed to the source that supplied each field. Treated as claims, not facts.

Production-grade, real-time threat detection for Python LLM and agentic applications. Guardian SDK protects the full agentic loop — input to the model, output from the model, every tool call an agent makes, every value tools return into the agent's context, and the compiled/parallel execution plans agent runtimes dispatch — across text, images, audio, and video. 170+ threat categories, 1,700+ regex patterns, 3,400+ semantic fingerprints on the API tier. Also available fully self-hosted (pip install ethicore-engine-selfhost) — the complete engine, compiled and sealed, runs in the customer's own infrastructure with no request data leaving. Listed in the NIST OLIR Catalog against NIST CSF 2.0, NIST AI RMF 1.0, and NIST SP 800-53 Rev 5, and mapped to the OWASP GenAI LLM Top 10 for 2026 (6 covered directly at runtime, 4 complemented). Assessed Awardable on the U.S. Department of War Tradewinds Solutions Marketplace.

safetypre-flightprompt-scanningthreat-detectionagentic-securityllm-protectionreal-timepost-flightoutput-scanningresponse-filteringjailbreak-detectionphi-protectiontool-call-validationpre-executionshell-injectionexfiltration-detectionllm-agentindirect-injectionrag-protectiontool-output-scanningcontext-poisoningexecution-planagent-swarmdag-validationscope-enforcementpurpose-controlscopeguardnarrow-botredirectin-purposefulfillment

Declared skills

Pre-flight Input Analysis — Scan an incoming prompt or agentic input before it reaches the model. Runs multiple sequential detection layers: regex pattern matching with obfuscation normalization, ONNX MiniLM-L6-v2 semantic analysis, behavioral session heuristics, ML gradient-boosted inference, and visual/cross-modal analysis for image inputs. Returns ALLOW, CHALLENGE, or BLOCK with threat level, threat types, confidence, and reasoning. Covers 170+ threat categories on the API tier.
Post-flight Response Analysis — Scan an LLM response before it reaches the user or downstream agents. Detects jailbreak compliance, constraint removal acknowledgments, system prompt revelation, role abandonment, credential/PHI leakage, and other signals that indicate the model was successfully manipulated. Returns suppressed (bool) and a safe replacement response when suppression is triggered. AdversarialLearner simultaneously updates the threat database for improved pre-flight detection.
Agentic Tool Call Validation — Validate a tool call and its arguments before the agent executes it. Detects shell injection, path traversal, data exfiltration infrastructure, destructive operations (rm -rf, DROP TABLE), credential theft attempts, package installs from untrusted sources, and malicious flag combinations. Returns is_dangerous (bool), risk_score, and threat_categories. The same gate scales to compiled/parallel execution plans (DAGs): the AgenticExecutionMonitor decomposes a plan, validates each node, and flags d…
Tool Output Injection Scan — Scan a tool return value before it re-enters the agent's context window. Detects indirect prompt injection payloads embedded in web pages, documents, API responses, database records, and any external content the agent retrieves. Returns is_injection (bool), injection_score, and matched patterns.
Agentic Execution Plan Validation — Validate a compiled/parallel agent execution plan (DAG) before the runtime dispatches it. Decomposes the plan, validates each node through the tool-call gate, and flags dangerous calls hidden in 'atomic'/parallel no-inspect batches, guard-disable steps ordered before payloads, hidden nodes absent from the approval summary, dependency cycles, and agent-swarm fan-out escalation across a session. Returns ALLOW/CHALLENGE/BLOCK with risk_score, node_count, dangerous_node_ids, and signals.
Scope Enforcement: In-Purpose Check (ScopeGuard) — ScopeGuard (a separate, paid-only product on the Ethicore Engine platform): decide whether a user turn is in-purpose for a narrow bot, given the deployer's declared scope (allow_domains + deny_task_types). Returns IN_SCOPE, BORDERLINE, or OUT_OF_SCOPE with a graceful redirect_message on out-of-scope - a redirect, not a security block. Fuses four FP-first signals: a general-purpose-task anchor, semantic scope distance, multi-turn drift, and output-side fulfillment. Configure a scope policy once …

kind A2A Agent Card

name A2A Agent Card

summary A2A Agent Card

version A2A Agent Card

description A2A Agent Card

homepageUrl A2A Agent Card

publisherUrl A2A Agent Card

publisherName A2A Agent Card

Derived by Wellknown

Capabilities

Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.

commerce.ecommerceE-commerce Operationsdeclared dev.terminalTerminal & Shell62%automation.orchestrationAgent Orchestration62%data.vector-searchVector Search58%

Provenance

Where this record came from

Every source is kept verbatim. Field changes are logged as events.

A2A Agent Cardhttps://oraclestechnologies.com/.well-known/agent.json

first seen 18 d ago · fetched 3 d agoopen ↗

Field history (7 recent events)

18 d ago · declared · summary → "Production-grade, real-time threat detection for Python LLM and agentic applications. Guardian SDK protects the full ag
18 d ago · declared · description → "Production-grade, real-time threat detection for Python LLM and agentic applications. Guardian SDK protects the full ag
18 d ago · declared · publisherName → "Oracles Technologies LLC"
18 d ago · declared · publisherUrl → "https://oraclestechnologies.com"
18 d ago · declared · homepageUrl → "https://portal.oraclestechnologies.com/docs"
18 d ago · declared · version → "2.7.0"
18 d ago · declared · protocols → ["a2a"]

Scope Enforcement: Output Fulfillment Check (ScopeGuard) — ScopeGuard post-flight signal: inspect the bot's generated RESPONSE for proof it produced off-scope content (a fenced code block, a worked math solution, a poem, a translation). High-precision fulfillment detection that catches what the input-side check missed. Returns OUT_OF_SCOPE when the response fulfilled a denied task type.