# Android Audit

> >

- **Type:** Skill
- **Install:** `agentstack add skill-felixgraeber-claude-android-audit-skill-android-audit`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [FelixGraeber](https://agentstack.voostack.com/s/felixgraeber)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [FelixGraeber](https://github.com/FelixGraeber)
- **Source:** https://github.com/FelixGraeber/claude-android-audit-skill/tree/main/skills/android-audit

## Install

```sh
agentstack add skill-felixgraeber-claude-android-audit-skill-android-audit
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Android Full Audit

## Flow

1. Run `scripts/build_audit_context.py` and write `generated/audit-context.json`
2. Dispatch the relevant agents with that JSON as the shared input
3. Collect category findings and category scores if available
4. Run `scripts/score.py` to apply deterministic gates and caps
5. Generate:
   - `ANDROID-AUDIT-REPORT.md`
   - `ANDROID-ACTION-PLAN.md`

## Reporting Rules

- Separate verified findings from preflight warnings.
- Mark any runtime-only or policy-only claim as `external evidence required`.
- Do not emit a final 0-100 score if category scores were not produced.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [FelixGraeber](https://github.com/FelixGraeber)
- **Source:** [FelixGraeber/claude-android-audit-skill](https://github.com/FelixGraeber/claude-android-audit-skill)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-felixgraeber-claude-android-audit-skill-android-audit
- Seller: https://agentstack.voostack.com/s/felixgraeber
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.