Follow Discord
Sweep 22 Oct 2026 · 04:32Z Build v2.1.308 527 read Stable v2.1.308 Latest v2.1.308 Next v2.1.308 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsClaude Developer Platform 21 Oct 2026
One change · api

environments changedmanaged-agents/environments

Nearest release: v2.1.307, published an hour after this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

Recorded here
Lines+5added
Lines−5removed
From line 23 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits20to this page, all time

The whole hunk

from line 23, old and new numbered
/
lines
from line 23
2323 -H "anthropic-version: 2023-06-01" \
2424 -H "anthropic-beta: managed-agents-2026-04-01" \
2525 -H "content-type: application/json" \
26 --data '{
26 -d '{
2727 "name": "python-dev",
2828 "config": {
2929 "type": "cloud",
from line 49
4949 ```
5050 </File>
5151 
52 [`ant apply`](https://platform.claude.com/docs/en/cli-sdks-libraries/cli/apply) creates the environment from `environment.yaml`, prints its ID, and records it in `claude-lock.json`. Commit `claude-lock.json` so the next `ant apply` updates this environment instead of trying to create it again.
52 [`ant apply`](https://platform.claude.com/docs/en/cli-sdks-libraries/cli/apply) creates the environment from `environment.yaml`, prints its ID, and records it in `claude-lock.json`. Commit `claude-lock.json` so the next `ant apply` updates this environment instead of attempting to create it again.
5353 </CodeGroupItem>
5454 
5555 ```python Python
from line 161
161161 -H "anthropic-version: 2023-06-01" \
162162 -H "anthropic-beta: managed-agents-2026-04-01" \
163163 -H "content-type: application/json" \
164 --data '{
164 -d '{
165165 "agent": "'"$AGENT_ID"'",
166166 "environment_id": "'"$ENVIRONMENT_ID"'"
167167 }'
from line 240
240240 -H "anthropic-version: 2023-06-01" \
241241 -H "anthropic-beta: managed-agents-2026-04-01" \
242242 -H "content-type: application/json" \
243 --data '{
243 -d '{
244244 "name": "data-analysis",
245245 "config": {
246246 "type": "cloud",
from line 623
623623* **The agent can change things on external sites, not only read them:** The `bash` tool can send any request. The agent can post data, submit forms, call APIs, and run scripts that change data on external sites. Even a request that only fetches a URL can change data on some sites.
624624* **Nothing pauses these requests by default:** The agent toolset's default [permission policy](https://platform.claude.com/docs/en/managed-agents/permission-policies) is `always_allow`, so `bash` commands run without approval.
625625* **Anything in the sandbox can leave it:** This includes files, tool outputs, and any credentials or secrets you put in the sandbox.
626* **Fetched content can steer the agent:** Web pages, API responses, and other content the agent reads can contain instructions (prompt injection) that change what it does next.
626* **Fetched content can steer the agent:** Webpages, API responses, and other content the agent reads can contain instructions (prompt injection) that change what it does next.
627627* **The agent acts on your behalf:** Its actions can violate a site's terms of service, or create accounts and records there.
628628* **Model behavior is not a security control:** The agent can act on external sites in ways you did not ask for, including retrying in a different way after a site blocks a request. Use network settings and permission policies to limit what it can do.
629629* **The safety blocklist is not an allowlist:** It does not limit which other sites the agent reaches, or what the agent does on them.
Feedback