Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/allsmog/vuln-scoutnpx agentmods add commands/allsmog/vuln-scout/mobile-auditWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/allsmog/vuln-scout/mobile-audit)<a href="https://agentmods.dev/commands/allsmog/vuln-scout/mobile-audit"><img src="https://agentmods.dev/badge/commands/allsmog/vuln-scout/mobile-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/allsmog/vuln-scout/mobile-audit"><img src="https://agentmods.dev/badge/commands/allsmog/vuln-scout/mobile-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00027 | $0.01592 |
| Opus 5 | $0.00014 | $0.00796 |
| Sonnet 5 | $0.00005 | $0.00318 |
| Haiku 4.5 | $0.00003 | $0.00159 |
Grade A, and why
mobile-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mobile Audit
End-to-end mobile audit driver for Android targets. Most Android bug-bounty work involves a decompiled APK that's been split into two directories:
| Directory | Holds | What we scan for |
|---|---|---|
jadx_out/sources/ |
Java/Kotlin pseudocode | WebView JS injection, remote-controlled URLs, insecure crypto, sensitive SharedPreferences, hardcoded secrets, @JavascriptInterface exposure |
apktool_out/ |
AndroidManifest.xml, res/xml/network_security_config.xml, native libs | Exported components, NSC pinning gaps, debuggable builds, allowBackup, deeplink hosts |
Pointing the regular /vuln-scout:scan at the target root misses one or the
other. This command auto-discovers both, runs the orchestrator on each, and
writes a single merged findings.json to the target's .claude/.
Usage
/vuln-scout:mobile-audit ~/bug-bounty/<target>
/vuln-scout:mobile-audit ~/bug-bounty/target --profile deep --output /tmp/out.json
# Apply a previously-triaged FP allowlist
/vuln-scout:mobile-audit ~/bug-bounty/target --suppressions ~/bug-bounty/target/.vuln-scout-ignore
The driver also auto-discovers <target>/.vuln-scout-ignore if --suppressions
is not given.
# Limit CI output to the two highest-impact chains
/vuln-scout:mobile-audit ~/bug-bounty/target --top-chains 2
# Ultra-quick smoke scan — skip chain detection entirely
/vuln-scout:mobile-audit ~/bug-bounty/target --no-chains
# Discover the chain pattern slugs to use in .vuln-scout-ignore rules
/vuln-scout:mobile-audit --list-chain-patterns
# Same, but emit JSON for tooling integration
/vuln-scout:mobile-audit --list-chain-patterns --list-chain-patterns-format json
# Lint a .vuln-scout-ignore file — warns on unknown chain slugs,
# invalid severity levels, and empty patterns. Exits non-zero on issues.
# Accepts either a file path or a target directory (auto-finds the
# .vuln-scout-ignore inside it).
/vuln-scout:mobile-audit --validate-suppressions ~/bug-bounty/target/.vuln-scout-ignore
/vuln-scout:mobile-audit --validate-suppressions ~/bug-bounty/target
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 159 lines · 27 tokens per session scan A 26f02fb93256
mobile-audit is a command published in the GitHub repository allsmog/vuln-scout (24 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 1,592 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
swift-critique
Critique SwiftUI code for patterns, design, clean code, accessibility, and performance.
mobile-specialist
Use when a design will be used on phones. Touch targets too small, controls outside thumb reach, bottom navigation, gestures, safe areas and notches, or behaviour with no connection.
apollo-check
Investigate the Apollo repository $ARGUMENTS and produce a detailed investigation for migration.
perf-investigate
Drive an iOS performance or memory-leak investigation on using Memory Graph + Time Profiler. Enforce data-before-architecture and stacked PRs.
feat
Kick off tasks creation for a new feature (4-item interview before invoking pm-agent; an epic-sized requirement routes to phased decomposition, a feature already built on one platform routes to cross-platform parity, a change that touches no endpoint routes to client-only).
fix
Apply code-level fixes for ALL validated findings, one at a time — modifies the target repository's source code.