AI agents invoke hijack_release to trigger actions in Mcp Bbs. 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.
This tool terminates a manual hijack/override session and hands control back to an automated bot. It triggers an external operational state change — resuming autonomous bot execution on a live BBS telnet session. This is an Execute-category action because it triggers external operations (bot automation) whose effects depend on the current session state.
From the tool's definition "Release hijack session and resume bot automation"
Attacks that exploit this kind of access
Release hijack session and resume bot automation. It is categorised as a Execute tool in the Mcp Bbs MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Bbs MCP server in PolicyLayer and add a rule for hijack_release: 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 Mcp Bbs. Nothing to install.
hijack_release 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 hijack_release 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 hijack_release. 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.
hijack_release is provided by the Mcp Bbs MCP server (livingstaccato/mcp-bbs). 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 →