AI agents invoke stop_test_session to trigger actions in Yo Bug. 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.
stop_test_session triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Attacks that exploit this kind of access
Stop test mode. Shuts down the reverse proxy and any auto-started dev server. Returns a test session summary. It is categorised as a Execute tool in the Yo Bug MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Yo Bug MCP server in PolicyLayer and add a rule for stop_test_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 Yo Bug. Nothing to install.
stop_test_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 stop_test_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 stop_test_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.
stop_test_session is provided by the Yo Bug MCP server (wyykerwin/yo-bug). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.