No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by straylabs-ai · Agent Tool · ★ 311
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is deadend-cli safe to install? View the security audit →
Deadend CLI [!IMPORTANT] It's been a few months that we didn't upload any new release. And the reason is that we are working on a better version for the harness (our current pro version that we plan to release). We will post the roadmap soon but here is some information (open to discussion in the discord), - Adapatable harness to work with other coding agents. - Authentication handling - WAFs bypasses - and much more Join us on the discord to discuss more about it ! Autonomous pentesting agent using feedback-driven iteration Achieves 80% on the full XBOW validation benchmark with Kimi K2.5 at US$122 total API cost for that end-to-end run, with a model-agnostic architecture that supports other deployable LLMs. Like the project or want to know more? Feel free to reach out! [!WARNING] Active Development: This project is undergoing active development. Core features are stable and production-ready, but we're continuously improving the interface, workflows, and adding new capabilities based on user feedback. Check out the roadmap or open a issue for a future issue. [!NOTE] For discussions, research, and feature ideas, join the community Discord: [Deadend CLI Discord](https://discord.gg/
| Stars | 311 |
| Forks | 53 |
| Language | Python |
| Category | Agent Tool |
| License | AGPL-3.0 |
| Quality Score | 74.0410829004237/100 |
| Open Issues | 10 |
| Last Updated | 2026-08-07 |
| Created | 2025-07-22 |
| Platforms | cli, python |
| Est. Tokens | ~18k |
These tools work well together with deadend-cli for enhanced workflows:
Looking for a deadend-cli alternative? If you're comparing deadend-cli with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Agentic pentest tooling. Currently achieving 81% (KIMI K2.5) on XBOW's benchmark in full black-box. Completely
A growing collection of MCP servers bringing offensive security tools to AI assistants. Nmap, Ghidra, Nuclei,
AI-powered offensive security testing using autonomous agents, directly in your terminal.
EVA is an AI-assisted penetration testing agent that enhances offensive security workflows by providing struct
Tactical AI Workspace Monitor & EDR
A secure file system for your agents to execute code
Explore other popular agent tool tools:
deadend-cli is Agentic pentest tooling. Currently achieving 81% (KIMI K2.5) on XBOW's benchmark in full black-box. Completely Self-hosted. Every model available on LiteLLM (Ollama, anthropic, openai...). It is categorized as a Agent Tool with 311 GitHub stars.
deadend-cli is primarily written in Python. It covers topics such as agentic-ai, ai, cybersecurity.
You can find installation instructions and usage details in the deadend-cli GitHub repository at github.com/straylabs-ai/deadend-cli. The project has 311 stars and 53 forks, indicating an active community.
deadend-cli is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.
The top alternatives to deadend-cli on Agent Skills Hub include deadend-cli, mcp-security-hub, apex. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: