> ## Documentation Index
> Fetch the complete documentation index at: /docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Investigate a finding

> From a finding on the Findings page to the session, the machine and a decision, in one pass.

A finding is one place where what an agent declared it would do and what the machine saw it do came apart. The **Findings** page lists them; this is the path from a row to a decision. Setting a verdict needs the Policy Writer role or higher.

**1. Pick the finding**

Open **Findings**. Filter by severity (**critical**, **high**, **medium**, **low**), by family (**intent vs truth**, **supply chain**) and by verdict (**Unjudged** is where new work is). In the **Findings** panel choose **Flat** and sort **By severity** to work from the top.

Each row shows **Severity**, **Finding** (name and type id), **What happened**, **Score**, **Verdict**, **Session** and **Age**.

**2. Read what was declared and what was observed**

Open the row. The **Overview** tab pairs the declared action with the observed one; the **Evidence** tab shows **Detector evidence**: the recorded facts the finding rests on. **Raw** shows the same as data.

**Framework mappings** names the controls this type of finding maps to. The page says it plainly: "it is not a compliance opinion."

**3. Follow it into the session**

Use **Open session** or **View in timeline**. The session opens on **Investigate**: **Activity** lists its recorded actions, **Conversation** what was said. **Context** holds **Session info** (working directory, agent, platform, model, parent session) and **Child sessions**; **Behavior** holds **Process lineage** when the sensor tied processes to the session. Look at what happened just before and after the finding.

**4. Check the machine**

Open the session's **Host** link. The host page shows **Last heartbeat** in its header, the capture lanes and install checks the sensor reported on **Capture**, and its agents on **Agents**. A **degraded** host, or a **Capture** tab saying "Lane states are last-known readings", may be missing evidence, which changes how much weight the finding carries.

**5. Ask Sentinel if the picture is unclear**

**Investigate in Sentinel** asks Sentinel about the finding in a new conversation beside the page. Sentinel answers from your workspace's own rows and shows every query it ran. See [Ask Sentinel](/docs/dashboard/sentinel.md).

**6. Record a verdict**

Back on the finding, set **True positive**, **False positive** or **Suspicious**. Verdicts are filters on the list, so an unjudged queue stays short. **Export CSV** exports the current list.

**7. Track it, or draft a rule**

Only a critical alert opens an **Incident** on its own. For anything else you want tracked to resolution, open **Incidents** and work the record. The panel beside it has three menus: **Status** (**Open**, **Investigating**, **Resolved**; an older record may show **Contained** or **Closed**), **Owner** and **Verdict**. The button at the top offers the next step: **Assign to me** while nobody owns the record, then **Set verdict**. The **⋯** menu holds **Copy link**, **Copy id**, **Open the first session** and **Status…**. Add a note under **History** with **Add note**. Assigning to another person needs Admin or Owner.

The panel also links **Draft a shadow rule**, which opens **Policies › Rules**, where you draft the rule. See [Write and publish a rule](/docs/policies/write-and-publish-a-rule.md).

## What the risk names mean

| Category | Finding names |
| - | - |
| Credential access | Credential read; Credential store modified |
| Exfiltration | Credential read, then egress |
| Persistence | Persistence implant |
| Execution | Undeclared command; Undeclared subprocess activity; Command differs from declared |
| Unexpected change | Undeclared file write; Declared path deleted |
| Intent mismatch | Read-only tool wrote a file; Path differs from declared; Action differs from declared |
| Approval bypass | Agent approved its own action; Agent-steered approval |
| Tool supply chain | MCP tool redefined; Tool description injection; Built-in tool changed; Tool cross-reference |

Every page uses these names. On the Overview and in **Top detectors** on the **Findings** page, types outside this list are counted as "Other findings"; a single finding of such a type shows its type id.

On macOS, in an upcoming agent release, **Command differs from declared** judges the program that ran (under a declared `ls`, a shell starting `curl` is reported; a test runner starting `git` is not), and **Undeclared command** names that program.

With that release, when an agent runs a Python tool by its own name, such as `pytest`, `pip install` or `uv run pytest`, the further copies of Python it starts (test workers, package builds) are not recorded as a match, as is already the case for `python3 -m pytest`. On Homebrew and Apple framework Python this removes matches earlier versions recorded; anything of another kind those copies start, such as `curl`, is still recorded. A versioned interpreter such as `python3.12` that a build tool starts as a separate process, for example `cd pkg && python3.12 -m pytest` in a `make test` recipe, is newly recorded when the command does not name it; a recipe line the build tool runs in place is not, as before. There is at most one match per program per command, and at most 32 programs per command.

Which programs a command counts as naming, including the limits for inline commit messages, is described in [How a command is read](/docs/dashboard/how-commands-are-read.md).

## Tool supply-chain findings

First-time checks, invisible characters and cross-references arrive in an upcoming agent release. Not checked: tools in OpenAI Chat, Bedrock Converse or Gemini formats; text inside a parameter schema.

| Finding | What it means | Severity | Next step |
| - | - | - | - |
| **Tool description injection** | A third-party MCP tool's description carries instructions aimed at the model. Checked on a change and, from that release, when Quint first sees the tool; invisible characters the model can read are flagged too. From that release, a provider's routine rewording of a built-in tool is usually not flagged; today it can be. | **Medium** the first time, **high** on a change. | Read the recorded excerpt on the finding's **Evidence** tab. If you don't trust it, remove the server or pin a reviewed version. |
| **Tool cross-reference** | One MCP server's tool description names a tool from a different MCP server offered at the same time. It matches names only: a lead, not proof. | **Low**. | Check you installed and expect both servers; remove any you don't. |

## If the list is empty

"No divergences in this window." is a result for the window you chose. A note that counts are unavailable is not: it is a coverage gap, not a quiet fleet. Widen the window, then check **Coverage** on the Overview and the **Silent** filter on **Data Sources** before concluding the fleet was quiet.

## Next

* [Decide an approval](/docs/dashboard/decide-an-approval.md) when a finding comes from a workload with approvals.
* [Shadow enforcement](/docs/policies/shadow-enforcement.md) to see what a rule would have done about it.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.