[CONFIDENTIAL ESCROW] Create a fully encrypted on-chain escrow using Fhenix FHE. The escrow amount is encrypted BEFORE hitting the blockchain — no one can see it on Arbiscan. Only the payer, payee, and platform can decrypt the amount. Currently available on: Arbitrum Sepolia (421614) only. Uses t...
Risk signalsHandles credentials or secrets (token)
Part of the Kustodia Escrow server.
Free to start. No card required.
AI agents use create_confidential_escrow to create or modify resources in Kustodia Escrow. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call create_confidential_escrow repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Kustodia Escrow.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"create_confidential_escrow": {
"limits": [
{
"counter": "create_confidential_escrow_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Kustodia Escrow policy for all 36 tools.
These attack patterns abuse exactly the kind of access create_confidential_escrow gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
[CONFIDENTIAL ESCROW] Create a fully encrypted on-chain escrow using Fhenix FHE. The escrow amount is encrypted BEFORE hitting the blockchain — no one can see it on Arbiscan. Only the payer, payee, and platform can decrypt the amount. Currently available on: Arbitrum Sepolia (421614) only. Uses the ConfidentialEscrowV2 contract with CoFHE threshold encryption. AFTER CREATION: Fund via fund_confidential_escrow, release via release_confidential_escrow.. It is categorised as a Write tool in the Kustodia Escrow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kustodia Escrow MCP server in PolicyLayer and add a rule for create_confidential_escrow: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Kustodia Escrow. Nothing to install.
create_confidential_escrow is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_confidential_escrow rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for create_confidential_escrow. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
create_confidential_escrow is provided by the Kustodia Escrow MCP server (kustodia/escrow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 36 Kustodia Escrow tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.