Check prompt injection defenses and security measures
AI agents call robustness.evaluate_prompt_injection_resistance to retrieve information from ContextForge MCP Gateway without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a read-only assessment of security posture. 'Check' and 'evaluate' are diagnostic verbs implying observation and reporting of existing conditions, not creation, modification, execution, or deletion of resources. While security-focused, it fits the Read category as it retrieves/queries security metrics and returns findings without triggering external operations or changing system state.
From the tool's definition Tool description states 'Check prompt injection defenses and security measures'—uses passive language ('check') indicating inspection or assessment of existing defenses rather than modification or execution.
Attacks that exploit this kind of access
Check prompt injection defenses and security measures. It is categorised as a Read tool in the ContextForge MCP Gateway MCP Server, which means it retrieves data without modifying state.
Register the ContextForge MCP Gateway MCP server in PolicyLayer and add a rule for robustness.evaluate_prompt_injection_resistance: 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 ContextForge MCP Gateway. Nothing to install.
robustness.evaluate_prompt_injection_resistance 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 robustness.evaluate_prompt_injection_resistance 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 robustness.evaluate_prompt_injection_resistance. 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.
robustness.evaluate_prompt_injection_resistance is provided by the ContextForge MCP Gateway MCP server (jrmatherly/mcp-context-forge). 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 →