Public references
Rules mapped to public security guidance.
Our guardrails line up with the public guidance written for AI agents. A reviewer can read the overlap in one place, with the frameworks we map against named plainly.
Sill holds no security certification today. This page is a reference, not a certificate. You remain responsible for your own compliance.
Mappings
Control by control, line by line.
GUARDRAILS YOU CONFIGURE
| CONTROL | OWASP AGENTIC 2026 | OWASP LLM 2026 | MITRE ATLAS 2026.10 | NIST AI RMF |
|---|---|---|---|---|
| Allowlisted agents only | ASI03, ASI10 | — | Initial Access | Manage |
| Require a signed order from the customer | ASI01, ASI03 | LLM06 | — | Manage |
| 60 calls per minute, per agent | ASI08 | LLM10 | Impact | Manage |
| 100 calls per minute, per IP | ASI08 | LLM10 | Impact | Manage |
| Per-transaction spend cap | ASI01 | LLM06, LLM10 | Impact | Manage |
| Daily spend cap, per customer | ASI08 | LLM06, LLM10 | Impact | Manage |
| Human review for refunds and cancellations | ASI08, ASI09 | LLM06 | Impact | Manage |
| No fake-urgency orders | ASI09 (partial) | — | — | — |
| No drip pricing | ASI09 (partial) | — | — | — |
| Block instruction-override text | ASI01 | LLM01 | AML.T0051 (partial) | Measure |
| Country allow / deny | — | — | Initial Access | Manage |
| Site-wide rate cap | ASI08 | LLM10 | Impact | Manage |
| Cart stays under the customer’s budget | ASI01 | LLM06 | — | Manage |
| Cart currency matches the authorization | ASI01 | LLM06 | — | Manage |
| One customer, one customer’s data | ASI03 | LLM06 | Exfiltration | Manage |
| Approved agent toolsets only | ASI02, ASI04 (partial) | LLM03 (partial) | AML.T0011.002 (partial) | Measure |
| No silent subscriptions | ASI09 | LLM06 | — | Manage |
| Block invisible-character attacks | ASI01 | LLM01 | AML.T0051 (partial) | Measure |
| Block orders that contain secrets | ASI02 (partial) | LLM02 (partial) | AML.T0098 (partial) | Measure |
| Short-lived order authorizations | ASI03 | LLM06 | Evasion | Manage |
| Order payload size limit | — | LLM10 | — | — |
| Emergency kill switch | ASI08 | LLM10 | Impact | Manage |
| Budget cap, per customer organization | ASI08 | LLM06, LLM10 | Impact | Manage |
| Your own rule (advanced) | merchant-defined | merchant-defined | merchant-defined | — |
ALWAYS ON
| CONTROL | OWASP AGENTIC 2026 | OWASP LLM 2026 | MITRE ATLAS 2026.10 | NIST AI RMF |
|---|---|---|---|---|
| Signature check on every signed request | ASI03, ASI10 | — | Initial Access, Evasion; AML.T0096 | Manage |
| Block replayed orders | ASI03 | — | Evasion | Measure |
| Lock out after repeated auth failures | — | LLM10 | Credential Access | Manage |
| Reject a request bound to another site | ASI03 | — | Evasion | Manage |
| Anti-fingerprinting on identity reads | — | — | Discovery | — |
| Signed webhooks only | — | — | — | Manage |
| Evaluation budgets with a safe default when exceeded | ASI08 | LLM10 | Impact | Manage |
| Tamper-evident, linked audit chain | ASI06 (partial) | — | — | Measure, Manage |
| Personal data redacted at the storage layer | — | LLM02 (partial) | Exfiltration | Manage |
| Scrub agent-visible responses | — | LLM02, LLM05, LLM07 | — | — |
| Delegation chain verified before trust is granted | ASI07 (registered-agent) | — | — | Manage |
| Signed cart cannot be edited | ASI01 | LLM06 | — | Manage |
OUT OF SCOPE
Risks that come from training or hosting a model
Sill does not train, host, or retrieve for models.
Unexpected code execution
Sill is an authorization layer, not an execution sandbox.
Agent-to-agent delegation outside a registered agent
Delegation from a registered agent is covered. Chains that start outside a registered agent are outside what Sill verifies.
The agent’s own runtime, host or build chain
Those live inside the agent, outside the request Sill sees.