bash
Run a shell command (bash -c) inside an allowed directory. Pipelines and && chaining work. Blocked commands (sudo, rm -rf, dd, mkfs, …) are always rejected. Risk 3.
This record as markdown: /tools/yuga-hashimoto-localant/bash.md
What bash does on LocalAnt
AI agents invoke bash to trigger actions in LocalAnt. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why bash is rated High
This tool executes shell commands whose effects depend on the arguments provided by an AI agent. While some protections (blocklist of rm -rf, dd, mkfs, sudo) are in place, an agent can still run arbitrary code with side effects (file modifications, process spawning, network calls, etc.). The blocklist is incomplete; many dangerous patterns exist outside explicitly blocked commands.
From the tool's definition Tool name is 'bash' and description states 'Run a shell command (bash -c)' with support for 'Pipelines and && chaining'. Despite blocklisting of dangerous commands, arbitrary shell execution remains possible.
Attacks that exploit this kind of access
The rule that runs bash safely
PolicyLayer is an MCP gateway: it sits between your AI agents and LocalAnt, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For bash, this is the rule to start with:
bash stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect LocalAnt, apply this rule, and every bash call is checked against it from then on.
Questions about bash
Run a shell command (bash -c) inside an allowed directory. Pipelines and && chaining work. Blocked commands (sudo, rm -rf, dd, mkfs, …) are always rejected. Risk 3. It is categorised as a Execute tool in the LocalAnt MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the LocalAnt MCP server in PolicyLayer and add a rule for bash: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches LocalAnt. Nothing to install.
bash is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the bash rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for bash. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
bash is provided by the LocalAnt MCP server (yuga-hashimoto/localant). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on LocalAnt, and thousands of servers like it.
Across the catalogue