by felinics · Agent Tool · ★ 121
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
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 | 121 |
| Forks | 10 |
| Language | Rust |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 57/100 |
| Open Issues | 1 |
| Last Updated | 2026-08-29 |
| Created | 2026-03-13 |
| Platforms | rust |
| Est. Tokens | ~22k |
Autofish English | 中文 Android control infrastructure for agents and multi-agent systems. Autofish gives any agent a stable, explicit, and observable Android execution layer: inspect the screen, act through stable refs instead of brittle coordinates, verify outcomes after every step, and recover with local execution memory.
These tools work well together with Autofish for enhanced workflows:
Looking for a Autofish alternative? If you're comparing Autofish 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.
An AI Agent tool to automate Android devices reliably
Give any AI agent a real phone: Android over ADB, iPhone over WebDriverAgent. 66 MCP tools, a Skill Hub with 1
Let an AI use your Android phone: an app and an SDK with 160+ MCP tools (calendar, SMS, files, camera, notific
Jetpack Compose Agent Skill — AI-powered coding guidance with actual androidx/androidx source code receipts. W
Android automation from code. Test your apps on real phones, script the tasks you repeat, run a shelf of phone
Open Android AI agent runtime for phone control, app automation, VLM screen reading, skill routing, mini apps,
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: