Delete a blob from project storage and decrement the project
AI agents call assets_rm to permanently remove resources in Run402 — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs irreversible data deletion from project storage. Even though it operates on 'blobs' (binary assets) rather than database records, deletion is permanent and cannot be reversed. The high severity reflects that an autonomous agent could destroy project assets without recovery options.
From the tool's definition Tool name 'assets_rm' and description 'Delete a blob from project storage and decrement the project' explicitly state irreversible deletion ('Delete') of stored data ('blob from project storage'). The action cannot be undone.
Attacks that exploit this kind of access
Delete a blob from project storage and decrement the project. It is categorised as a Destructive tool in the Run402 MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Run402 MCP server in PolicyLayer and add a rule for assets_rm: 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 Run402. Nothing to install.
assets_rm is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the assets_rm 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 assets_rm. 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.
assets_rm is provided by the Run402 MCP server (kychee-com/run402). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →