Scan text and block if injection is detected above threshold.
AI agents call injection_check to retrieve information from Agent Safety without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Although the tool can 'block' based on detection results (implying gating), the core operation is scanning/analyzing text for malicious patterns and returning a signal. This is information retrieval with no side effects on external systems—typical of a security validation layer. No code execution, data modification, deletion, or financial impact occurs.
From the tool's definition Tool scans and detects injection patterns in text input; performs analysis without modifying, deleting, or executing code.
Attacks that exploit this kind of access
Scan text and block if injection is detected above threshold. It is categorised as a Read tool in the Agent Safety MCP Server, which means it retrieves data without modifying state.
Register the Agent Safety MCP server in PolicyLayer and add a rule for injection_check: 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 Agent Safety. Nothing to install.
injection_check is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the injection_check 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 injection_check. 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.
injection_check is provided by the Agent Safety MCP server (luciferforge/agent-safety-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 →