SECURITY POSTURE

Built by people who’ve read the breach post-mortems.

FAIL_CLOSED by default. HMAC-signed audit. Offline ML. AES-256-GCM at rest. Nothing leaves your network unless you configure an outbound provider.

01

Threat model

Ten attack vectors. Ten places Verosek catches them.

Attack vectorWhere Verosek catches it
Tool poisoning (malicious tool description)Policy engine CHK-001, Shield CHK-020
Prompt injection — directShield CHK-013 / CHK-014 multilingual classifier
Prompt injection — indirect via tool outputShield CHK-020 — the capability competitors can’t ship
Identity confusion (prompt overrides permissions)Identity check at gateway; permissions in execution layer
Cross-tool privilege escalationSession drift CHK-022 cumulative tracking
One-time auth persistence (MCP tokens never expire)TTL on virtual keys + CHK-012
Uncontrolled destructive operations (DROP TABLE)CHK-003 / CHK-004 block DROP and DELETE
PII / secret exfiltrationCHK-005, CHK-009, CHK-015, CHK-016, CHK-018, CHK-019, CHK-021
Hallucination of grounded-looking answersCHK-023 offline grounding verdict
Scope creep (agent answers about unauthorised topics)CHK-024 off-topic embedding similarity
02

Data handling

Your data stays in your network.

In transit

TLS 1.3 to your configured providers. mTLS between gateway and ML container if enabled.

At rest

MCP credentials encrypted with AES-256-GCM. Signing keys stored in env / secrets manager of your choice.

Key storage

No multi-tenant key pool. Your deployment, your keys, your rotation cadence.

03

Fail-safe

FAIL_CLOSED by default. FAIL_OPEN is opt-in, per key.

Default

FAIL_CLOSED

Gateway unreachable → tool calls blocked, structured error returned. The only safe default for keys with write access or sensitive data.

Opt-in

FAIL_OPEN

Gateway unreachable → tool calls pass with an alert flag in the audit. For read-only, low-sensitivity agents where availability wins.

04

PII handling

Four redaction modes. One PII engine.

mode: tag

Preserve the string; tag the span in the audit trace.

mode: fake

Replace with a realistic synthetic value of the same entity type.

mode: mask

Replace with asterisks (e.g. ****-****-****-1234).

mode: hash

Replace with a salted SHA-256. Deterministic per session.

05

Offline + air-gap

Every ML model ships inside your image.

No outbound inference calls. No third-party API telemetry. The Shield ML container runs entirely on-premises or in your VPC. Verify with verosek-verify-offline before going live.

06

Responsible disclosure

Found a vulnerability? Email us.

info@verosek.com — PGP key on /trust. We acknowledge within one business day, triage within five, and fix or mitigate within thirty for validated high-severity issues.

Request the security whitepaper.

Threat model, data flows, cryptographic primitives, and a mapping of our checks to MITRE ATLAS.