Record detection feedback for pattern learning. Improves future detection accuracy. 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_c...
AI agents use aidefence_learn to create or update resources in Ruflo — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ruflo environment.
This tool writes feedback records to a learning system to improve future pattern detection. It modifies the internal state of a detection model (the learned patterns), which is a Write operation — reversible in principle (feedback could be corrected), not destructive.
From the tool's definition 'Record detection feedback for pattern learning. Improves future detection accuracy.' — the tool writes/records feedback data to update a detection model.
Attacks that exploit this kind of access
Record detection feedback for pattern learning. Improves future detection accuracy. 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 Write tool in the Ruflo MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ruflo MCP server in PolicyLayer and add a rule for aidefence_learn: 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 Ruflo. Nothing to install.
aidefence_learn is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the aidefence_learn 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_learn. 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_learn is provided by the Ruflo MCP server (ruvnet/ruflo). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
aidefence_learn is one line of Ruflo's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →