ClawHub

Android Dev Agent

v1.0.0

Assist with AOSP builds, HAL analysis, Framework edits, ROM customization, and SDK/NDK issues using isolated environments and detailed reports.

⭐ 0· 43·1 current·1 all-time
by@happysurfingeveryday-art
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description (AOSP builds, HAL/Framework/ROM work) align with the instructions: creating isolated worktrees, running build/analysis commands, and producing reports. The skill does not request unrelated credentials or config paths.
ℹ
Instruction Scope
SKILL.md explicitly instructs the agent to read source/docs, create work directories under memory/, run build/analysis commands (m, lunch, repo sync, find, etc.), and write reports and patches. This is expected for an Android dev agent, but it implies the agent will execute arbitrary shell build commands and fetch large upstream repositories — the user should ensure those actions occur in a sandboxed environment and that no sensitive local files are present in the agent's workspace.
✓
Install Mechanism
Instruction-only skill with no install spec and no code files. No downloads or archive extraction are declared, so nothing is written to disk beyond the agent's normal working-memory artifacts.
✓
Credentials
The skill does not request environment variables, credentials, or config paths. That is proportional to its stated goal; no unrelated secrets are requested.
✓
Persistence & Privilege
always is false and model invocation is allowed (default). The skill does not request persistent/always-on presence or to modify other skills or system-wide settings.
Assessment
This skill appears coherent with its Android development purpose. Before enabling it, be aware that it expects to clone AOSP trees and run heavy build/analysis commands (network, disk, CPU). Run it only in an isolated/sandboxed workspace or CI runner to avoid large downloads or accidental access to sensitive local files. If you require stricter controls, ask the publisher for explicit limits on network access, disk usage, and exact commands the agent will run.

Like a lobster shell, security has layers — review code before you run it.

latestvk97760992wmsbybk9p56kejndd84t7ca

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments