Skip to content

Update the Claude agent step injection check default to Claude Haiku 5.5 #3506

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We鈥檒l occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
zentron wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Update the Claude agent step injection check default to Claude Haiku 5.5 #3506

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion src/pages/docs/octopus-ai/claude-agent-step/getting-started.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,7 +63,7 @@ To add and configure the step:
9. Optionally, under **Agent Capabilities**, add **Skills**, connect the **Octopus MCP Server**, or add **Additional MCP Servers**. See [Extending the Claude Agent Step](/docs/octopus-ai/claude-agent-step/tools).
10. Under **Additional Configuration Options**, set a **Turn Limit** to cap how many turns the agent can take before the step stops. One turn is a single request/response cycle with the model. The default is 10.
11. Optionally, set a **Maximum Budget** as a spend cap in USD. Leave it blank for no limit.
12. Leave **Prompt Injection Check** switched on. Before the agent runs, Octopus screens the prompt, deployment variables, MCP configuration, and skills with a fast model (`claude-haiku-4-5` by default) and blocks the step if it detects an injection attempt.
12. Leave **Prompt Injection Check** switched on. Before the agent runs, Octopus screens the prompt, deployment variables, MCP configuration, and skills with a fast model (`claude-haiku-5-5` by default) and blocks the step if it detects an injection attempt.
13. Save the step.

The **Run Claude Agent** step appears in your deployment process or runbook, ready to run.
Expand Down
2 changes: 1 addition & 1 deletion src/pages/docs/octopus-ai/claude-agent-step/security-and-compliance.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -143,7 +143,7 @@ Prompt injection is when untrusted content the agent reads tries to hijack it: a

**If the check itself can't run.** By default, the step fails if the check errors (for example, the model call fails). You can change this with the **Continue if the check cannot run** option, which lets the run proceed when the check can't complete.

**Defaults and caps.** The check uses `claude-haiku-4-5` by default (you can choose another model), produces at most 1024 tokens for its verdict, and truncates the execution context to 200,000 characters before checking. These caps bound the check's cost and latency.
**Defaults and caps.** The check uses `claude-haiku-5-5` by default (you can choose another model), produces at most 2048 tokens for its verdict, and truncates the execution context to 200,000 characters before checking. These caps bound the check's cost and latency.

The check adds a model call to every run, and its token usage appears in the task's Claude Usage Summary (though not its cost). A determined injection can be phrased to slip past a screening model, so treat this as the first line of defense.

Expand Down
Loading