MCP Path

File Input Risk Auto-Learn

File Input Risk Auto-Learn is a public reference for targeted browser interaction with a prechecked target. It names the signal, policy, or flow an agent should understand before choosing a concrete tool.

Catalog path

Reference page for a documented MCP capability path.

Type: MCP path
Family: Interaction (Click, Type, Forms)
Effect: sensitive
Status: Reference
Path: 5.19

Purpose

What this entry explains

What it does

This reference explains File Input Risk Auto-Learn for targeted browser interaction with a prechecked target. It is kept as a named reference so agents can cite the flow without inventing a tool name.

Use when

Use this entry when an agent needs to handle the sensitive path "File Input Risk Auto-Learn" for targeted browser interaction with a prechecked target.
Use it as a reference path when the catalog describes a capability but no single public tool name is explicit.
Use it before chaining follow-up tools so the next step is based on current evidence.

Reference Use

How agents should cite and apply this area

Examples are maintained at family level and use only public tool names or reference paths already present in the catalog.

Signal, gate, behavior, boundary

File Input Risk Auto-Learn describes a gate for targeted browser interaction with a prechecked target. The path shows which signal, gate, behavior, or boundary must be checked before choosing a concrete tool.

When agents cite it

An agent cites this path when it needs File Input Risk Auto-Learn as context for a decision, block, target check, or follow-up tool choice.

Why no callable name

The public source does not name one callable tool for this path. The documentation therefore keeps it as a reference path and does not invent a callable name.

Signals and rule

Relevant response signals: fileInputRisk, fileUploadSelectorHint, pksAutoLearn. Safety axes: Page interaction, Sensitive, User confirmation. The reference path alone is not permission to execute. Before acting, check current MCP discovery, visible target, scope, and the actual response.

Family example

A task in targeted browser interaction with a prechecked target can trigger powerful execution and therefore needs target, approval, and result check before the step.

The agent starts with nova.click_selector, reads the current response or reference, and only then chooses the concrete next tool.

nova.click_selector nova.type_selector nova.select_option

Current discovery, target, user control, warning signals, and result check come before execution.

Contract

Inputs and important response fields

This page is a public reference. Agents and integrators should still read current MCP tool discovery before execution, because schemas can be gated by settings or version.

Inputs

No stable public input field is derived from the catalog source for this path. Read current MCP discovery before execution.

Response field	Explanation
`fileInputRisk`	Response field named by the catalog source. Treat it as current evidence for the next decision.
`fileUploadSelectorHint`	Response field named by the catalog source. Treat it as current evidence for the next decision.
`pksAutoLearn`	Response field named by the catalog source. Treat it as current evidence for the next decision.

Safety

Boundary before execution

Effect

May touch sensitive data, permissions, credentials, identity, or external connection paths. Use only with explicit scope and visible user control.

Agent rule

Require explicit purpose and current context, avoid exposing secrets in prompts or logs, and stop when permission or identity state is unclear.

Human control

For humans, this entry marks the sensitive surface in targeted browser interaction with a prechecked target and keeps permission, credential, or external-connection handling explicit.

Safety Axes

How this path can affect work

Axes are stable catalog signals for humans, agents, and LLM discovery. One path can carry several axes.

Page interaction page_interaction

Clicks, types, selects, uploads, or interacts with visible page elements.

Execute only with a visible target, expected effect, and a follow-up result check.

Sensitive sensitive_data

Touches cookies, storage, clipboard, credentials, tokens, user content, identity, or private data.

Use only with bounded purpose and visible user control; do not guess, log, or forward sensitive values.

User confirmation user_confirmation

Requires visible confirmation, target review, approval, or deliberate user control.

Do not proceed until the required confirmation is visible or unambiguous in the current context.