An antivirus for AI agents that trade.
SENTRY LAYER is a runtime security layer for autonomous agents trading tokenized stocks on Robinhood Chain — WAF · EDR · DLP for the agent stack. It inspects every prompt, market feed, model output and on-chain trade inline, and blocks the ones that shouldn't execute.
Antivirus was built for files.
Attacks now travel in meaning.
A classic AV matches deterministic bytes. Attacks on a trading agent are semantic, probabilistic and contextual — the same message is harmless or catastrophic depending on whether the agent can move your tokenized shares. You can't sign a payload that rephrases itself infinitely.
So we keep what carries over — layered defense, hybrid detection, a live threat feed, quarantine, telemetry — and rebuild the rest as runtime security for on-chain agents.
Classic AV
- file signatures
- known-bad bytes
- static scan
- on-disk quarantine
SENTRY LAYER
- semantic detection
- intent & provenance
- inline runtime
- trade-level firewall
The threat model
Eleven classes across input, market data, output, and on-chain trades — mapped to OWASP LLM Top 10 & MITRE ATLAS.
Cheap filters first. Expensive models last.
A hybrid conveyor — each stage only escalates what the previous couldn't resolve.
Normalize
base64 · hex · zero-width · NFKC · homoglyph
Signatures
regex + fuzzy TI feed
Embeddings
similarity to attack corpus
Guard model
fine-tuned classifier
LLM-as-judge
escalation for the grey zone
Try the working console.
The whole detection pipeline runs client-side in your browser. No data leaves the page.
Launch App ▸