Open-source guardrail

Review API endpoint changes for auth

AgentTrail Guard lets this run by default, and writes the match to its local decision log so you can see how often it happens.

Default action
Warn
Severity
Medium severity
Library version
0.2.8Nov 11, 2026

Mapped to the OWASP Top 10s

An id names a risk this guardrail addresses where it becomes a command or a file read or write, never the whole risk. It warns by default, so the action still runs and is recorded.

What it catches, and what it misses

Written into the rule itself, next to what it matches, so you can judge it before you trust it.

Routes edits to API route/handler SOURCE files to human approval so a reviewer can confirm authentication is present on new or changed endpoints. Matched by path: a source file under routes/, handlers/ or controllers/; an api/ directory nested inside a source tree (src/api/, app/api/, pages/api/); Next's route.ts convention; and the <name>.controller.* / <name>.routes.* spellings. Reading is excluded — the Read and Grep tools never match — so opening an endpoint's source to read it does not ask for approval; every other file tool does, including one this corpus does not know. HEURISTIC: a path signal only — it cannot inspect the edit for a missing auth check or exposed PII, so treat a match as confirm auth on this endpoint, not as a finding. It deliberately does NOT match every file in a package merely NAMED api, nor a client-side router table such as routes.tsx, which defines no endpoint; and it MISSES endpoints declared inline in a server file or by a framework convention not listed above.

Tested on every build

The rule must match every command on the left and none on the right, or the library does not build. Catching the real thing is easy; staying quiet on the near-miss is the hard part.

Catches (4)

  • Editsrc/api/users.ts
  • Editapp/users/route.ts
  • Editpages/api/session.ts
  • Editsrc/controllers/payments.ts

Stays quiet on (6)

  • Editapps/api/README.md
  • Editapps/api/package.json
  • Editapps/api/src/lib/logger.ts
  • Editapps/web/src/app/routes.tsx
  • Readsrc/api/users.ts
  • Grepsrc/controllers/payments.ts

What "warn" means in each app

The guard runs as a hook in each app, and each app gives a hook different powers. Here is what this rule's default action does in each one.

Claude Code
The call runs, and the match is written to the local decision log.
Cursor
The call runs, and Cursor shows nothing. The match is still written to the decision log.
Codex CLI
The call runs. Codex's terminal UI shows a hook line (a codex exec run shows nothing), and the match is written to the decision log.

This rule matches file paths. In Codex CLI, reading a file fires no hook, and in Cursor, reads shown as Explored are not checked, so there it sees fewer calls than in Claude Code. Each app hands the guard a different set of calls: in a Cursor sandbox run mode, for one, some terminal commands run without reaching the guard at all. Read the notes for Cursor and for Codex CLI before you rely on a rule there.

Change what it does in one command

Turn it off, change its action, or silence it on one command shape. The narrow one is allow: the rule keeps catching everything else.

agenttrail-guard
$agenttrail-guard guardrails show require-auth-on-pii-endpoints# everything about it
$agenttrail-guard guardrails set-action require-auth-on-pii-endpoints ask# block, ask or warn
$agenttrail-guard guardrails allow require-auth-on-pii-endpoints '<pattern>'# silence one shape
$agenttrail-guard guardrails disable require-auth-on-pii-endpoints# turn it off

Put these guardrails in front of your agent.

AgentTrail Guard is free and open source. It checks every command and file change against the whole library before your agent runs it, on your machine, with no account.

bash
$npm i -g @agenttrail/guard
Read the source on GitHub