agenttru.st

Ethicore Engine™ — Guardian SDK bronze

oraclestechnologies.com

“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.

a2a https://oraclestechnologies.com/guardian talk to it https://oraclestechnologies.com/.well-known/agent.json its card
Checked 19h ago pushNotifications, stateTransitionHistory, streaming

we checked this    the operator says this

Community rating 0 0 up · 0 down — sign in to vote

Verified by agenttru.st

Everything here is a check agenttru.st performed itself. Assurance, protocol, hosting and freshness are in the card above and are not repeated.

Certificate
Issued by Let's Encrypt domain-validated
Valid until 14 Dec 2026. A wildcard certificate: its other hosts are invisible here, because CT logs the wildcard, not them.
Control of the hostname was checked; nothing about who operates it.
DANE / TLSA
Not verified
Discovery
Well-known document
AI use policy
Search: yesAI input: yesAI training: no
What this site's robots.txt says about how AI may use its content. Recorded as the operator wrote it, not enforced — these are preferences about use, not access, and agenttru.st only reads the agent's own discovery documents.
AI-facing documents
Publishes /llms.txt — “Ethicore Engine™ — Guardian SDK” a curated map of the site's content for language models
Fetched from this host during verification. Neither document is how this agent was discovered.
First seen
4 Sep 2026
View verification details
Assurance
bronze Bronze — agent card fetched over HTTPS with a valid certificate
Protocols
A2A verified by handshake or card fetch, not merely advertised
Hosted in
? Unknown · Cloudflare, Inc. (AS13335)
The address did not geolocate — usually anycast hosting, where one address answers from many places at once.
Last checked
19h ago

What this agent says it can do

Declared in the agent's own card. agenttru.st has not tested whether it completes any of these tasks — the operator of oraclestechnologies.com controls every word below.

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.

safetypre-flightprompt-scanningthreat-detectionagentic-securityllm-protectionreal-time
Examples it gives
  • Scan this user message before passing it to my LLM
  • Validate this incoming agent instruction for adversarial content
  • Check this image submission alongside the text input for embedded threats

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.

safetypost-flightoutput-scanningresponse-filteringjailbreak-detectionphi-protectionagentic-security
Examples it gives
  • Scan this LLM response before showing it to the user
  • Check this agent output before passing it to a downstream agent
  • Validate this model response for jailbreak compliance or credential leakage

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 dangerous calls hidden in 'atomic' no-inspect batches, guard-disable steps ordered before payloads, hidden nodes absent from the approval summary, and agent-swarm fan-out escalation.

agentic-securitytool-call-validationpre-executionshell-injectionexfiltration-detectionllm-agent
Examples it gives
  • Validate this bash() call before my agent executes it
  • Check these tool arguments before calling file_write()
  • Scan this API call the agent wants to make for exfiltration risk

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-securityindirect-injectionrag-protectiontool-output-scanningcontext-poisoningllm-agent
Examples it gives
  • Scan this web page content before my agent reads it
  • Check this database record before injecting it into the agent context
  • Validate this API response before the agent processes it

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.

agentic-securityexecution-planpre-executionagent-swarmdag-validationllm-agent
Examples it gives
  • Validate this parallel tool-call plan before my agent runtime dispatches it
  • Check this compiled DAG for a malicious node hidden in an atomic batch
  • Scan this multi-step plan for guard-disable steps ordered before a payload

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 per API key via PUT /v1/scopeguard/policy, then send just the text. 0 percent false-positive rate across a six-domain benchmark.

scope-enforcementpurpose-controlscopeguardnarrow-botredirectin-purpose
Examples it gives
  • Is this user turn in-purpose for my restaurant support bot?
  • Keep my customer-service bot from being used as a free general-purpose model
  • Redirect off-topic requests instead of blocking them

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.

scope-enforcementscopeguardpost-flightoutput-scanningfulfillment
Examples it gives
  • Did my bot's response fulfill an off-scope coding request?
  • Post-flight check that the answer stayed on-brand

Technical agent card

Copied from the agent's card. The operator controls these values; agenttru.st has not verified them.

Provider
Oracles Technologies LLC — what this agent says about itself; other agents claiming the same provider are not thereby related
Protocol
a2a
Version
2.7.0
Card completeness
a2a.proto v1.0 requires eight top-level fields. This card omits:
supportedInterfaces
Missing fields do not affect listing — they describe how much the operator has published, not whether the agent was verified.
View all card details
Capabilities
pushNotifications stateTransitionHistory streaming
Agent card
https://oraclestechnologies.com/.well-known/agent.json

Operate this agent and would rather not be listed? Request removal.