ClawdSecbot

Command execution guard. Must be used when a tool call executes an operating-system command through shell, terminal, process, task, exec, command, MCP, or computer-use command tools. Requires user confirmation for dangerous Linux, Windows, and macOS commands.

Script execution risk guard. Use when a tool call executes a script file or multi-line interpreter payload, or when command_execution_guard identifies a launcher command that points to a script. Focus on script content, hidden execution chains, and mismatch between user intent and script behavior.

Browser and web access risk guard. Use when tool calls open URLs, browse webpages, fetch web content, follow redirects, download web resources, or execute actions influenced by webpage content.

File and data exfiltration risk guard. Use when tool calls may move data outside trusted boundaries (network upload, external messaging, email attachment, cloud sync, or removable device transfer).

Sensitive file access and path abuse guard. Use when tool calls read/list/search filesystem paths and may touch credentials, system files, private documents, or high-impact configuration.

General guard for uncategorized tool risks and browser/web access safety. Use when a tool call does not cleanly match a specialized skill, or when webpage access/content can influence downstream tool behavior.

New skill/plugin/MCP installation guard. Use when tool calls download, clone, install, or enable external capabilities. Always require security scanning before trust.

Dependency and package supply-chain risk guard. Use when tool calls install packages, modify dependency manifests, change lockfiles, or execute install hooks.

Email operation risk guard for read/search/summarize/export/forward/delete workflows. Use when tool calls access mailbox content or change mailbox state.

Internal network and lateral movement guard. Use when tool calls target internal hosts, cloud metadata endpoints, remote admin channels, tunnels, or service enumeration.

Persistence and backdoor modification guard. Use when tool calls alter startup tasks, login scripts, service definitions, auth config, or long-lived execution footholds.

Resource exhaustion and denial-of-service guard. Use when tool calls may create unbounded CPU, memory, disk, process, or network consumption.

Guidance for identifying data theft patterns in skills

Guidance for detecting supply chain attacks in dependency files

Guidance for decoding hidden payloads in skills

Guidance for analyzing executable scripts found in skills

Guidance for detecting deceptive instructions in skill documentation

A helpful assistant that helps with daily tasks