Architecture-specific review

LangChain agent security review

A LangChain or LangGraph agent is a workflow with tools, state and external data, not just a model call. Review the paths the agent can take, the permissions its tools carry, what survives between runs, and which actions a person must approve.

Request access →

Review scope

What Drel establishes for this stack

Scope the deployed graph and its application services: model provider, tools, retrieval sources, checkpoint store and downstream systems. A framework's interrupt or checkpointer is a building block; the team's authorization, storage and approval design still needs evidence.

Drel rebuilds the system from its repository, maps the attack paths through each area, checks the controls it can verify in your code, and proposes the fix for each control that fails. A reviewer decides what counts as evidence.

01

Entry points and trust boundaries

Which user, document, tool result or webhook can enter the graph? Where can untrusted content influence a later model or tool step?

What counts as evidence: Graph definition, input and retrieval data-flow diagram, source labels, and your own tests across each lower-trust boundary.

02

Tool execution authority

Which tools can read, write or send data? Does each handler check the originating user's permission and constrain its own service credential?

What counts as evidence: Tool registry and schemas, handler authorization code, credential scopes, negative permission tests, and audit events for side effects.

03

State and checkpoint access

What conversation or graph state is persisted, how is it keyed to a user or tenant, and who can resume or inspect a prior run?

What counts as evidence: Checkpointer configuration, thread identifier design, storage access policy, retention policy, and cross-tenant read/resume tests.

04

Approval and resumption

Which consequential steps pause for a person? Can a resumed run bypass approval or use stale permissions after the pause?

What counts as evidence: Interrupt locations, approval UI and role checks, resume-path tests, expired-permission tests, and a record of who approved each action.

05

Failure paths and decision

What happens after a failed tool call, retry or partially completed action? Which gaps remain before the agent can reach production?

What counts as evidence: Retry and idempotency design, rollback or compensation tests, open controls with owners, and the signed review decision.

Architecture example

Follow authority and data end to end

A model endpoint is one component. The security decision also depends on the identity that calls it, the data it receives, the actions it can trigger, and who accepts the remaining risk.

For an agent that drafts and sends customer replies: customer message → retrieved account context → draft response → approval interrupt → send-email tool. Check that the retrieved account belongs to the requester, the approval applies to the exact draft, and the send tool rechecks authority when the run resumes.

From repository to approval

Drel models the system from its repository, threat-models every attack path against OWASP, the EU AI Act and 22 more, maps the attack paths through it, checks the controls it can verify in your code, proposes the fix in a Jira ticket, and re-checks the automatic checks you turn on when the branch you link changes. Your AI Committee signs the approval. Unknown or missing evidence remains visible; it is not treated as a passed control.

Read the review methodology →

Further reading