From 828ccbbbe4db016578cd8a868065afae981cda70 Mon Sep 17 00:00:00 2001 From: robert Date: Sun, 11 Oct 2026 21:42:36 +1000 Subject: [PATCH] Update the Claude agent step injection check default to Claude Haiku 5.5 --- src/pages/docs/octopus-ai/claude-agent-step/getting-started.md | 2 +- .../octopus-ai/claude-agent-step/security-and-compliance.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/src/pages/docs/octopus-ai/claude-agent-step/getting-started.md b/src/pages/docs/octopus-ai/claude-agent-step/getting-started.md index 1e5031c9ac..7a8332b69f 100644 --- a/src/pages/docs/octopus-ai/claude-agent-step/getting-started.md +++ b/src/pages/docs/octopus-ai/claude-agent-step/getting-started.md @@ -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. diff --git a/src/pages/docs/octopus-ai/claude-agent-step/security-and-compliance.md b/src/pages/docs/octopus-ai/claude-agent-step/security-and-compliance.md index 3cc84e07dd..f10ad7971b 100644 --- a/src/pages/docs/octopus-ai/claude-agent-step/security-and-compliance.md +++ b/src/pages/docs/octopus-ai/claude-agent-step/security-and-compliance.md @@ -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.