by straylabs-ai · Agent Tool · ★ 329
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
git clone https://github.com/xoxruns/deadend-cli.git
Taken from the project's README on GitHub.
None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 329 |
| Forks | 53 |
| Language | Python |
| Category | Agent Tool |
| License | AGPL-3.0 |
| Quality Score | 74/100 |
| Open Issues | 10 |
| Last Updated | 2026-08-07 |
| Created | 2025-07-22 |
| Platforms | cli, python |
| Est. Tokens | ~18k |
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.
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.
Tactical AI Workspace Monitor & EDR
A secure file system for your agents to execute code
RedTeam-MCP: AI-Powered Autonomous Red Team Framework via Model Context Protocol. AI红队与内网渗透自动化框架,支持 gogo, fsca
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: