High-risk tools in PraisonAI

High severity PraisonAI MCP Server 6 of 91 tools

6 of the 91 tools in PraisonAI are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.

Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.

Tools at high risk

bedrockBrowserNavigate Execute

Navigate to a URL using cloud-based browser automation.
bedrockCodeInterpreter Execute

Execute code in a secure AWS-managed sandbox. Supports Python, JavaScript, and TypeScript.
build Execute

Build context string
codeMode Execute

Execute code in a sandboxed environment with access to imported tools. Write files, run code, and get results.
executeCode Execute

Execute Python code in a secure sandbox environment. Use this for calculations, data processing, and computational tasks.
interactive Execute

Start interactive approval mode

Attacks that target this class

High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.

High-risk tools in PraisonAI

Tools at high risk

Attacks that target this class

More on PraisonAI

Let agents act without letting them run wild.