--- title: "Agent Commander: Prompt-Based Command and Control · Embrace The Red" url: https://daily.dev/posts/agent-commander-prompt-based-command-and-control-embrace-the-red-dbdduqa7p source_url: https://embracethered.com/blog/posts/2026/agent-commander-your-agent-works-for-me-now/ type: article source: "Embrace The Red" published: 2026-03-17T04:45:18.561Z updated: 2026-03-17T04:45:43.391Z tags: ["ai-agents", "ai-security", "prompt-injection", "red-teaming"] reading_time: 10 upvotes: 2 comments: 1 language: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Agent Commander: Prompt-Based Command and Control · Embrace The Red **[Embrace The Red](https://daily.dev/sources/embracethered)** · 10 min read · 2 upvotes · 1 comments ## Summary Agent Commander is a proof-of-concept command and control (C2) framework that hijacks AI agents using natural language prompts rather than OS commands. The research demonstrates how agents like OpenClaw, Kimi Claw, and NanoClaw can be compromised via indirect prompt injection—through malicious emails, documents, or websites—and made to periodically check in for new tasks. Persistence is achieved by modifying agent configuration files like HEARTBEAT.md. Once hijacked, agents can perform host enumeration, screenshot capture, data exfiltration, and influence campaigns, all directed through prompts. The post covers attack vectors, persistence mechanisms, sandboxing limitations, and defensive recommendations including prompt monitoring, integrity checks, kill-switches, and credential rotation. The author warns that as software becomes more 'organic,' attacks will become less predictable and harder to control. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Community discussion Top comments from developers on daily.dev. **@allinonetools** · 1 upvotes > This is a serious reminder that prompt injection is not just theoretical. If agents can be hijacked through normal inputs, then monitoring prompts and adding guardrails is not optional anymore—it is basic security. ## Similar posts on daily.dev - [Agents Commander: A Lightweight Interface for Multi-Agent CLI Workflows](https://daily.dev/posts/agents-commander-a-lightweight-interface-for-multi-agent-cli-workflows-acfuqdr7x) · Callstack Blog · 0 upvotes · 0 comments - [Rules fail at the prompt, succeed at the boundary](https://daily.dev/posts/rules-fail-at-the-prompt-succeed-at-the-boundary-0o3kqk0lm) · MIT Technology Review · 1 upvotes · 0 comments - [From Assistant to Adversary: Exploiting Agentic AI Developer Tools](https://daily.dev/posts/from-assistant-to-adversary-exploiting-agentic-ai-developer-tools-dl4yjs179) · NVIDIA Developer · 2 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#ai-security](https://daily.dev/tags/ai-security), [#prompt-injection](https://daily.dev/tags/prompt-injection), [#red-teaming](https://daily.dev/tags/red-teaming) [View this post on daily.dev](https://daily.dev/posts/agent-commander-prompt-based-command-and-control-embrace-the-red-dbdduqa7p)