This record as markdown: /tools/0xyg3n-claude-c2/inject.md
What inject does on Claude C2
AI agents invoke inject to trigger actions in Claude C2. 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.
Why inject is rated High
Injecting shellcode is one of the most severe offensive operations possible: it executes arbitrary machine code in a remote system's process space, enabling full compromise, privilege escalation, persistence, lateral movement, etc. Given the server context (bypassing UAC, AMSI, Defender exclusions, browser credential theft), this is clearly a malicious remote-access/C2 capability.
From the tool's definition 'Inject shellcode. Auto-selects client.' — shellcode injection is arbitrary native code execution in a remote process
Attacks that exploit this kind of access
The rule that runs inject safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Claude C2, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For inject, this is the rule to start with:
inject stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Claude C2, apply this rule, and every inject call is checked against it from then on.
Questions about inject
Inject shellcode. Auto-selects client. It is categorised as a Execute tool in the Claude C2 MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Claude C2 MCP server in PolicyLayer and add a rule for inject: 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 Claude C2. Nothing to install.
inject 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 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. 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 is provided by the Claude C2 MCP server (0xyg3n/claude-c2). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Claude C2, and thousands of servers like it.
Across the catalogue