---
type: "raw_signal"
id: "how-to-review-your-agents-for-security-issues-098194"
slug: "how-to-review-your-agents-for-security-issues-098194"
title: "How to review your agents for security issues (by Anthropic): Learn how to audit finished agent sessions for things like prompt injection, unauthorized hosts, leaked credentials, blocked calls that..."
description: "Anthropic published a Claude Cookbook workflow for reviewing completed agent sessions for security issues."
retrieval_nugget: "Anthropic published a Claude Cookbook workflow for reviewing completed agent sessions for security issues."
observed_at: "2026-10-20"
record_date: "2026-10-20"
date_kind: "observed_at"
why_it_matters: "Source: https://platform.claude.com/cookbook/managed-agents-cma-agent-security-review"
novelty: "notable"
verification_level: "source-linked"
signal_type: "update"
source_platform: "platform.claude.com"
topics: ["anthropic","claude","prompt-injection"]
entities: ["Anthropic","Claude Cookbook","Managed Agents","Messages API","Claude Agent SDK","Claude Haiku 5.5"]
related_patterns: ["agent-security-moves-to-runtime-boundaries"]
novelty_label: "new_fact"
what_changed: "Anthropic’s cookbook adds a practical audit for finished agent sessions, identifying risks such as prompt injection, unauthorized hosts and credential misuse, with ranked evidence-backed reviews."
prior_refs: ["memory:2081767e-29f1-8828-add0-611335b6f8ad","memory:ce5d0d5c-9645-827f-a4ff-8d314184270a"]
source_url: "https://platform.claude.com/cookbook/managed-agents-cma-agent-security-review"
source_urls: ["https://platform.claude.com/cookbook/managed-agents-cma-agent-security-review"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:how-to-review-your-agents-for-security-issues-098194"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/how-to-review-your-agents-for-security-issues-098194/","markdown":"https://newruntime.com/signals/how-to-review-your-agents-for-security-issues-098194.md","json":"https://newruntime.com/signals/how-to-review-your-agents-for-security-issues-098194.json"}
---

# How to review your agents for security issues (by Anthropic): Learn how to audit finished agent sessions for things like prompt injection, unauthorized hosts, leaked credentials, blocked calls that...

## Retrieval answer

Anthropic published a Claude Cookbook workflow for reviewing completed agent sessions for security issues.

Anthropic published a Claude Cookbook workflow for reviewing completed agent sessions for security issues. It checks for out-of-allowlist hosts, credentials the agent was not given, unapproved data transfers, retries after blocked calls, and instructions planted in content the agent read. It produces a ranked report with quoted evidence for human review.

The workflow can read Managed Agents sessions, Messages API logs, or Claude Agent SDK logs. In the cookbook's 20 example sessions, it flags four for action; all four are staged examples designed to exercise the review. Anthropic estimates that reviewing all 20 costs about $0.10 at list price using Claude Haiku 5.5. The source describes a review workflow, not independent evidence of detection performance on production traffic.

Source: https://platform.claude.com/cookbook/managed-agents-cma-agent-security-review

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Anthropic](https://newruntime.com/topics/anthropic.md): Explore the anthropic topic hub.
- topic hub: [Claude](https://newruntime.com/topics/claude.md): Explore the claude topic hub.
- topic hub: [Prompt Injection](https://newruntime.com/topics/prompt-injection.md): Explore the prompt-injection topic hub.
- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)