Check if input contains PII (emails, SSNs, API keys, passwords, etc.). 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_has_pii 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 is a read-only security validation tool. It retrieves and analyzes properties of input data (presence of PII patterns) with no side effects on data or systems. The severity is low because misuse causes information disclosure risk only if the tool itself is compromised, not from normal operation.
From the tool's definition Tool description explicitly states 'Check if input contains PII' — it performs detection/scanning without modification. The tool 'ingests untrusted input' but does not alter, delete, or execute code based on findings; it only analyzes and reports.
Attacks that exploit this kind of access
Check if input contains PII (emails, SSNs, API keys, passwords, etc.). 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_has_pii: 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_has_pii 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_has_pii 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_has_pii. 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_has_pii 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.