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-ios-app-group-and-pasteboard-exposuregit 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-ios-app-group-and-pasteboard-exposure)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-ios-app-group-and-pasteboard-exposure"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-ios-app-group-and-pasteboard-exposure/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-ios-app-group-and-pasteboard-exposure"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-ios-app-group-and-pasteboard-exposure.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 | $0.00188 | $0.02161 |
| Opus 5.5 | $0.00075 | $0.00864 |
| Sonnet 5.5 | $0.00038 | $0.00432 |
| Haiku 4.5 | $0.00019 | $0.00216 |
Grade A, and why
auditing-ios-app-group-and-pasteboard-exposure 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing iOS app group and pasteboard exposure: when a secret leaves the app through a shared door
An iOS app is meant to be a sealed container, but it has several legitimate doors through which data leaves: an app-group container it shares with its own extensions, a shared keychain access group, the general pasteboard any app can read, and the state the system captures in snapshots or hands to extensions. Each door is fine for data whose sensitivity tolerates the audience on the other side, and a leak when a secret goes through a door wider than it should. A token written to an app-group container is readable by every extension and app in that group; a secret in an over-broad shared keychain group is reachable by apps that should not have it; a value copied to the general pasteboard is readable by any app, including ones the user never launched deliberately; and sensitive data left on screen or in memory lands in a snapshot or an extension context. The bug is a sensitive value on a shared surface whose audience exceeds the app's own boundary. You audit these by listing what the app writes to each shared surface and who can read it.
When to use
- An iOS app shares data with its own extensions through an app group or a shared keychain access group.
- The app copies or exposes values through the general pasteboard or hands data to an extension.
- Sensitive data may appear in a snapshot, a shared container, or a channel other apps can read.
Scope check
Audit shared-surface exposure only on apps and devices you own or are authorized to assess, on test devices and accounts, recovering only test data from the shared surface rather than a real user's. A confirmed leak lets another app or process read the app's private data, so keep every probe within scope. If you can't name the authorization, stop.
The loop
- Establish the audience of each shared surface and the sensitivity of what is written to it first. For each shared surface the app uses, an app-group container, a shared keychain group, the general pasteboard, a snapshot, or an extension handoff, determine who can read it and whether the data written there tolerates that audience. This is the false-positive killer: a shared surface carrying only data whose sensitivity matches its audience is not a leak, and a sensitive value never written to a shared surface is not exposed. Name the surface, its audience, and the sensitive value before claiming a leak.
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 · 136 lines · 188 tokens per session scan A d6f060999977
auditing-ios-app-group-and-pasteboard-exposure is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 188 tokens to every session and 2,161 once invoked, about $0.0008 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.…