Inject SSH session
AI agents invoke inject_ssh to trigger actions in Cobalt Strike MCP Server. 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 actively injects (hijacks or spawns) an SSH session, which constitutes executing an external operation with significant lateral movement potential in a red team/attack context. Running on a Cobalt Strike C2 server amplifies the blast radius to critical, as misuse could result in unauthorized access to remote systems, privilege escalation, or full compromise of additional hosts.
From the tool's definition 'Inject SSH session' — injecting an SSH session on a remote system initiates an active, privileged remote shell or session on a target host
Attacks that exploit this kind of access
Inject SSH session. It is categorised as a Execute tool in the Cobalt Strike MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cobalt Strike MCP Server MCP server in PolicyLayer and add a rule for inject_ssh: 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 Cobalt Strike MCP Server. Nothing to install.
inject_ssh 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 inject_ssh 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 inject_ssh. 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.
inject_ssh is provided by the Cobalt Strike MCP Server MCP server (mickeydb/cobalt-strike-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 →