Security

Determine whether an agent action may run, needs approval or must be denied

Verify declared token audience and issuer after local cryptographic validation

Validate HTTPS callback and redirect destinations against an explicit host allowlist

Detect changes between a trusted tool baseline and its current manifest

Validate and sign a portable task, scope, budget and expiry handoff

Hash and label agent context by declared integrity, confidentiality and source

Compare multiple agent results and sign exact agreement or conflict evidence

Validate declared signature status, freshness and payload evidence

Detect compatibility or conflict between agent policies

Check declared dependency identity, source and digest coverage

Select among conflicting results using explicit policy

Calculate data age against an explicit freshness policy

Attest declared DNS and HTTPS domain-control proof status

Bind declared consent to action purpose, scope and expiry

Plan bounded idempotent resumption from a checkpoint

Report price bands only from settled observations

Normalize and compare multiple x402 quotes

Detect duplicate charge fingerprints

Enforce recurring period budgets

Hash and attest supplied delivery evidence

Enforce concurrent slot limits

Stop repeated execution nodes and step overruns

Assess tool reachability and observation staleness

Identify changed manifest fields and hashes