AI agents use save_storage_state to create or update resources in Wraith — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Wraith environment.
The tool writes data (storage state) which is reversible and has no immediate destructive or financial impact. However, in the context of a stealth browser used for bot detection bypass, misuse could facilitate unauthorized session persistence or credential storage. Assigned 'medium' severity due to the stealth/evasion nature of the server and the write operation's potential to enable malicious session manipulation.
From the tool's definition Tool name 'save_storage_state' indicates persistence of browser state/data. In the context of a 'stealth browser MCP server' with 'bot detection bypass', this tool likely writes or modifies stored browser session data, cookies, or local storage.
Attacks that exploit this kind of access
save_storage_state. It is categorised as a Write tool in the Wraith MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Wraith MCP server in PolicyLayer and add a rule for save_storage_state: 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 Wraith. Nothing to install.
save_storage_state 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 save_storage_state 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 save_storage_state. 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.
save_storage_state is provided by the Wraith MCP server (koreahwan/wraith-mcp). 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 →