Quick boolean check if input is safe. Fastest option for simple validation. Use when nothing native exists — Claude Code does not have a PII / prompt-injection / adversarial-text scanner. Pair with any tool that ingests untrusted input (browser scrape, federation envelope, memory_import_claude).
AI agents call aidefence_is_safe to retrieve information from Claude Flow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries or evaluates input data to determine safety status without modifying, creating, deleting, or executing external operations. It is purely an informational check that returns a boolean value. The blast radius of misuse is minimal since it only informs decisions rather than directly effecting changes. Classification as Read is appropriate for a validation/scanning function.
From the tool's definition Tool performs a "Quick boolean check if input is safe" and is described as a validation scanner for PII/prompt-injection/adversarial-text detection. It returns a boolean result with no side effects mentioned.
Attacks that exploit this kind of access
Quick boolean check if input is safe. Fastest option for simple validation. Use when nothing native exists — Claude Code does not have a PII / prompt-injection / adversarial-text scanner. Pair with any tool that ingests untrusted input (browser scrape, federation envelope, memory_import_claude). It is categorised as a Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.
Register the Claude Flow MCP server in PolicyLayer and add a rule for aidefence_is_safe: 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 Flow. Nothing to install.
aidefence_is_safe 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 aidefence_is_safe 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 aidefence_is_safe. 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.
aidefence_is_safe is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.