Skip to content

open-coder-ai/block-unguarded-agent-spawn

v0.0.1Apache-2.0

Best-effort guard against an agent launching a coding agent with its safety checks off: claude --dangerously-skip-permissions or --permission-mode bypassPermissions, codex --full-auto, --yolo, --dangerously-bypass-approvals-and-sandbox or --sandbox danger-full-access, gemini --yolo, -y or --approval-mode yolo, cursor-agent --force. A spawned agent that never asks and never sandboxes is an unsupervised agent (OWASP ASI10, rogue agents). Read as a parsed command, so cd repo && claude ..., bash -c '...', sudo/env wrappers and npx @openai/codex ... are caught, while a normal invocation, codex --sandbox workspace-write, or a command that only mentions the flag (echo, grep, a commit message) is not. Known bypass classes include shell aliases, wrapper scripts, config files that set the mode, and agents this list does not name. Run the agent with its default approvals; a human decides when an unattended run is acceptable.

GitHub
block-unguarded-agent-spawn

Best-effort guard against an agent launching a coding agent with its safety checks off: claude --dangerously-skip-permissions or --permission-mode bypassPermissions, codex --full-auto, --yolo, --dangerously-bypass-approvals-and-sandbox or --sandbox danger-full-access, gemini --yolo, -y or --approval-mode yolo, cursor-agent --force. A spawned agent that never asks and never sandboxes is an unsupervised agent (OWASP ASI10, rogue agents). Read as a parsed command, so cd repo && claude ..., bash -c '...', sudo/env wrappers and npx @openai/codex ... are caught, while a normal invocation, codex --sandbox workspace-write, or a command that only mentions the flag (echo, grep, a commit message) is not. Known bypass classes include shell aliases, wrapper scripts, config files that set the mode, and agents this list does not name. Run the agent with its default approvals; a human decides when an unattended run is acceptable.