Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add UnboundCompute/security-agent-skills --skill auditing-mobile-biometric-and-local-auth-bypassgit clone --depth 1 https://github.com/UnboundCompute/security-agent-skillsWrote 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/skills/unboundcompute/security-agent-skills/auditing-mobile-biometric-and-local-auth-bypass)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-mobile-biometric-and-local-auth-bypass"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-mobile-biometric-and-local-auth-bypass/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/skills/unboundcompute/security-agent-skills/auditing-mobile-biometric-and-local-auth-bypass"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-mobile-biometric-and-local-auth-bypass.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 | $0.00175 | $0.02106 |
| Opus 5.5 | $0.00070 | $0.00842 |
| Sonnet 5.5 | $0.00035 | $0.00421 |
| Haiku 4.5 | $0.00017 | $0.00211 |
Grade A, and why
auditing-mobile-biometric-and-local-auth-bypass 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 1mo 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing mobile biometric and local auth bypass: when the prompt says yes but proves nothing
A mobile app often guards a sensitive action or a stored secret behind a local authentication prompt: a fingerprint, a face, or the device passcode. That gate is meaningful only when passing it actually releases something the protected path needs, a key that decrypts the data, held so the data cannot be reached without a genuine authentication. It is theater when the app merely asks for the prompt and then trusts its own record of the answer: a success flag the app sets, a callback it believes, or a screen it hides. On a device the attacker controls, a boolean result can be forced, a callback can be forged, and a hidden screen's data is still in memory or on disk. The gate also fails when the released key is not invalidated after the enrolled biometrics change, so a newly added fingerprint unlocks the old secret, or when only the interface is gated while the protected data or action remains directly reachable. The bug is reaching the protected data or action without a genuine local authentication. You audit these by finding what the prompt actually releases and whether the protected path needs it.
When to use
- A mobile app gates sensitive data or an action behind a biometric or device-passcode prompt.
- The app may trust a success result or callback rather than a key the authentication releases.
- The protected data or action may be reachable without passing the prompt on a controlled device.
Scope check
Audit local authentication only on apps and devices you own or are authorized to assess, on test devices and accounts, demonstrating a bypass against test data rather than a real user's. A confirmed bypass reaches data or actions meant to require the user's presence, so keep every probe within scope. If you can't name the authorization, stop.
The loop
- Establish what the prompt actually releases and whether the protected path needs it first. For each local-auth gate, determine whether passing it releases a key that the protected data or action genuinely requires, so the path cannot complete without a real authentication, or whether the app trusts a result, a callback, or a hidden interface while the data or action remains reachable. This is the false-positive killer: a gate that binds the sensitive data to a key released only by a genuine authentication cannot be bypassed by forcing a result. Name what the prompt releases before crafting a bypass.
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.
- 1mo ago First seen · 139 lines · 175 tokens per session scan A bd5197fba1c9
auditing-mobile-biometric-and-local-auth-bypass is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 175 tokens to every session and 2,106 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-09-09.
Other skills, from other repositories
swiftui-expert-skill
Write, review, or improve SwiftUI code following best practices for state management, view composition, performance, macOS-specific APIs, and iOS 26+ Liquid Glass adoption. Use when building new SwiftUI features, refactoring existing views, reviewing code quality, or adopting modern SwiftUI patterns.
prodcheck-review
Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations, post-launch readiness and people. Use when asked to check whether a project is ready to ship, to audit an area before launch, or to work through a specific checklist. Produces evidence with file:line…
swiftui-expert-skill
Write, review, or improve SwiftUI code following best practices for state management, view composition, performance, macOS-specific APIs, and iOS 26+ Liquid Glass adoption. Use when building new SwiftUI features, refactoring existing views, reviewing code quality, or adopting modern SwiftUI patterns.
analyzing-ios-app-security-with-objection
Runtime iOS app security testing with Objection (Frida): inspect keychain and filesystem data, explore app internals at runtime, and validate/bypass client-side protections during authorized mobile assessments.
analyzing-android-malware-with-apktool
Perform static analysis of Android APK malware samples using apktool for decompilation, jadx for Java source recovery, and androguard for permission analysis, manifest inspection, and suspicious API call detection.
mobile-pentest
Mobile app pentest for bug bounty (Android APK + iOS IPA) — runtime-first workflow: install app, proxy through Burp/mitmproxy, drive the UI, capture packets, then test the API exactly like a web target; escalate to decompile (apktool/jadx) and Frida/objection only when traffic is SSL-pinned, encrypted, or absent.…