AI agents call assets_sign to retrieve information from Run402 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and grants temporary read access to stored data (S3 blobs) without creating, modifying, or deleting content. The time-boxing mitigates some risk, but if misused by an agent, it could expose sensitive private blobs to unauthorized external parties, hence medium severity rather than low. The confidence is high because the description explicitly indicates GET-only access.
From the tool's definition Tool description states 'Generate a time-boxed S3 presigned GET URL for a blob' and 'share a private blob externally', indicating retrieval of data via pre-signed URLs with no modification or deletion.
Attacks that exploit this kind of access
Generate a time-boxed S3 presigned GET URL for a blob. Use this to share a private blob externally without exposing your apikey. Default TTL 1 hour, max 7 days. It is categorised as a Read tool in the Run402 MCP Server, which means it retrieves data without modifying state.
Register the Run402 MCP server in PolicyLayer and add a rule for assets_sign: 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_sign is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the assets_sign 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_sign. 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_sign 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 →