v0.8.0: opens a headed Chromium tab on
AI agents invoke seed_auth_session to trigger actions in Custom Browser. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool opens a headed (visible) Chromium browser tab, which constitutes triggering an external operation. The name 'seed_auth_session' suggests it also establishes or seeds an authentication session, which involves writing session/cookie state. Opening a browser tab with auth context could expose credentials or session tokens to misuse.
From the tool's definition 'opens a headed Chromium tab' — launches a browser process/tab, which is an external operation with side effects beyond simple data retrieval
Attacks that exploit this kind of access
v0.8.0: opens a headed Chromium tab on. It is categorised as a Execute tool in the Custom Browser MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Custom Browser MCP server in PolicyLayer and add a rule for seed_auth_session: 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 Custom Browser. Nothing to install.
seed_auth_session is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the seed_auth_session 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 seed_auth_session. 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.
seed_auth_session is provided by the Custom Browser MCP server (theriz78/eclectique-browser-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 →