Scan text for prompt injection patterns. Returns risk assessment without blocking.
AI agents call injection_scan 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.
This is a security analysis tool that examines text content and reports findings. It has no capability to modify data, execute commands, delete information, or trigger external systems. The blast radius of misuse is minimal—an adversary could only obtain false negatives on injection detection or DoS the scanning service, neither of which causes data loss or financial harm. Classification as Read is appropriate.
From the tool's definition Tool name 'injection_scan' and description 'Scan text for prompt injection patterns. Returns risk assessment without blocking' indicates the tool performs detection and analysis only.
Attacks that exploit this kind of access
Scan text for prompt injection patterns. Returns risk assessment without blocking. 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_scan: 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_scan 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_scan 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_scan. 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_scan 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 →