AI agent scope of action

An agent's scope of change is a per-tool list of the systems it touches and the one kind of change each tool makes: read, comment, ticket, configure, block or delete. OWASP LLM06:2025, read 19 Nov 2026, traces excessive agency to three roots: functionality, permissions and autonomy.

The two questions

  • Q02. Which production systems and which kinds of change (read, comment, ticket, configure, block, delete) is the agent allowed to touch, written down per tool?
  • Q03. Does any tool give the agent an open-ended capability (run a shell command, fetch any URL) where a narrow function would do?

Q02 asks for a register. Q03 asks what to do with the entries that no register row can describe. Together they turn "the agent has access to our ticketing system" into a list a reviewer can approve or strike line by line.

What a good answer contains

  • Every tool the harness exposes has a row, including tools that came with a framework by default.
  • Each row names one system and one of the six kinds. A row that says "any", or needs two kinds, is a Q03 finding: split it into two tools.
  • Open-ended capabilities (shell, arbitrary URL fetch) are absent, or carry a written reason, a named owner and a date by which they are replaced.
  • The register is stored where the harness reads it, so the tool list and the document cannot drift apart.

What the requirement says

OWASP states the cause plainly: "The root cause of Excessive Agency is typically one or more of: excessive functionality; excessive permissions; excessive autonomy." Its first mitigation is to "Limit the extensions that LLM agents are allowed to call to only the minimum necessary." Its example is narrow: an extension that reads a mailbox to summarize emails "may only require the ability to read emails, so the extension should not contain other functionality such as deleting or sending messages" (OWASP LLM06:2025, read 19 Nov 2026).

On open-ended tools OWASP says to "Avoid the use of open-ended extensions where possible (e.g., run a shell command, fetch a URL, etc.) and use extensions with more granular functionality." If a file write is built on a shell command, "the scope for undesirable actions is very large (any other shell command could be executed)"; a file-writing function that does only that is the safer build.

A register that uses the six kinds

The checklist names six kinds but does not define them. This page reads them as follows. Read: no state changes. Comment: adds text to an existing record. Ticket: creates a record that a person must act on, including a pull request. Configure: changes a setting on a system. Block: adds an entry to a deny list. Delete: removes data or a record.

Example register for a vulnerability triage agent, written for this page to show the shape of an answer. Tool names and limits are illustrative, not taken from a vendor or a standard.
ToolSystemKindLimit written in the toolUndo
read_findingScanner APIReadFindings of the 4 projects assigned to the jobNot needed
add_ticket_commentQueue SEC-VULNCommentTickets the agent openedComment deleted by an owner
open_fix_requestSource repositoryTicketPushes one branch named agent/ plus the CVE id and opens one pull request; cannot mergeClose the request
set_asset_tagAsset inventoryConfigureOne tag key, patch-window; value from a fixed list of 3Previous value is in the log
block_package_versionArtifact registryBlockOne named package version per call; no wildcardsRemove the deny entry
delete_agent_branchSource repositoryDeleteOnly branches under agent/ that the agent createdRestore from the commit id in the log

Worked example: replacing a shell tool with narrow functions

A triage agent shipped with one general tool, run_shell. Q03 flags it. The method: export every call of the last 30 days from the log and group them by what each call did.

412 calls in 30 days (301 + 62 + 31 + 11 + 7). Figures are an example; run the same grouping on your own log.
What the calls didCallsKindNarrow replacement
curl GET requests to the scanner API301Readread_finding
git push and pull request creation (60 to agent/ branches, 2 to a colleague's feature branch)62Ticketopen_fix_request; the 2 pushes to a colleague's branch would now be refused
git branch -D on agent/ branches31Deletedelete_agent_branch
cat, jq and grep on exported files11ReadNone: read_finding already returns what these read
kubectl get deployment, to see which image tag runs7Readread_deployed_image (a seventh row, Kubernetes, read only)

Two results matter. First, 100% of the calls fit a read, ticket or delete tool, so run_shell can be removed instead of wrapped. Second, the 30 days contain no call that is a configure or a block, so set_asset_tag and block_package_version stay in the register only if the job specification names a need for them; otherwise the reviewer strikes both rows. The two pushes to a colleague's branch are the reason the open_fix_request limit names the agent/ prefix: the shell allowed them, and nobody had approved them.

How to test it on your own systems, and how it fails

  1. Export the tool list the running agent actually receives, not the design document, and diff it against the register. Any tool in one and not the other is a finding. Owner: the harness maintainer. Record: the diff, dated, kept with the register.
  2. For every open-ended tool, group the last 30 days of calls as in the table above and write each distinct purpose as a narrow function. A purpose that cannot be written as one function stays a Q03 finding with a written reason, a named owner and a replacement date. Owner: the tool's owner. Record: the grouping table and the finding.
  3. Ask the owner of each downstream system to confirm the kind of change in the register against what the agent's account can do. Owner: that system's owner. Record: the confirmation, with the date and the account checked.
  4. Run the diff again whenever a tool is added, and after every framework or SDK upgrade; re-evaluating after model changes lists the triggers. Owner: whoever approves the change. Record: the new diff, signed off before release.

The usual failure is drift. A framework upgrade or a new integration adds a default tool, the register still lists six rows, and nobody reviews the seventh until it is used. Step 1 catches it only if it runs on every upgrade, which is why step 4 ties the diff to the release and not to a calendar.

How tool lists are built is in the agent harness section on tools and permissions; the use-case map shows which jobs vendors describe as read-only and which as write.

Sources

  1. OWASP, LLM06:2025 Excessive Agency, prevention and mitigation strategies, read 19 Nov 2026

Last reviewed 19 Nov 2026