Waxell

skill

ios-qa High risk

garrytangarrytan/gstackupdated

Live-device iOS QA for SwiftUI apps. Use for: ios qa, test the iphone app, test the ipad app. (gstack)
garrytan's own description, from the skill's files.
Stars
142,230
Version
v2
Copies
0

Overview

blockHigh risk

Waxell rates it high risk: 16 findings, highest severity high.

Highest severity
high
Findings
16
What ran
Static analysis + deep scan

A clean result means nothing alarming in what is published, not a guarantee. How the checks work

We don't republish the skill's instructions. Read them on GitHub at the reviewed commit.

Security

Security scan

Checked yesterday

Result

High risk Waxell rates it high risk: 16 findings, highest severity high.

Checked with static analysis + deep scan: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. The deep scan also read the instructions for prompt injection and data exfiltration. Nothing was run. How the checks work

Findings (16)

high · 3

  • high

    Excessive Agency: External Model or Provider Selection

    SKILL.md:39 · skillspector:EA5

  • high

    The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing per

    daemon/src/allowlist.ts:1 · skillspector:LP1

  • high

    The skill uses 'network' capability that is not listed in its permissions. This may indicate deceptive intent or missing

    daemon/src/index.ts:1 · skillspector:LP1

medium · 13

  • medium

    Rogue Agent: Session Persistence

    SKILL.md:9 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    SKILL.md:9 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    SKILL.md:80 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    SKILL.md:287 · skillspector:RA2

  • medium

    Memory Poisoning: Context Window Stuffing

    SKILL.md:393 · skillspector:MP2

  • medium

    Memory Poisoning: Context Window Stuffing

    SKILL.md.tmpl:292 · skillspector:MP2

  • medium

    Rogue Agent: Session Persistence

    SKILL.md.tmpl:23 · skillspector:RA2

  • medium

    Excessive Agency: Unbounded Resource Access

    daemon/src/index.ts:349 · skillspector:EA4

  • medium

    Rogue Agent: Session Persistence

    daemon/src/session-cache.ts:33 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    daemon/src/single-instance.ts:126 · skillspector:RA2

  • medium

    Rogue Agent: Session Persistence

    docs/tailscale-acl-example.md:54 · skillspector:RA2

  • medium

    Data Exfiltration: External Transmission

    docs/tailscale-acl-example.md:85 · skillspector:E1

  • medium

    Rogue Agent: Session Persistence

    sections/preamble.md:22 · skillspector:RA2

Versions

Version history

Each distinct content we have seen, newest first, with the verdict it got at the time.

  1. v2 (1.0.0)2026-11-201 changed High risk
  2. v1 (1.0.0)2026-11-19 High risk

Files

Files

45 files, 503 KB in total. Names only; open them on GitHub.

  • SKILL.md
  • SKILL.md.tmpl
  • daemon/src/allowlist.ts
  • daemon/src/audit.ts
  • daemon/src/auth-mint.ts
  • daemon/src/cli-mint.ts
  • daemon/src/devicectl.ts
  • daemon/src/index.ts
  • daemon/src/proxy.ts
  • daemon/src/session-cache.ts
  • daemon/src/session-tokens.ts
  • daemon/src/single-instance.ts
  • daemon/src/tailscale-localapi.ts
  • daemon/src/tunnel-bootstrap.ts
  • daemon/src/types.ts
  • daemon/test/allowlist.test.ts
  • daemon/test/audit.test.ts
  • daemon/test/auth-mint.test.ts
  • daemon/test/cli-mint.test.ts
  • daemon/test/daemon-integration.test.ts
  • daemon/test/devicectl-launch-env.test.ts
  • daemon/test/fake-device.ts
  • daemon/test/loopback-request.test.ts
  • daemon/test/proxy-classify.test.ts
  • daemon/test/proxy-transport.test.ts
  • daemon/test/session-cache.test.ts
  • daemon/test/session-tokens.test.ts
  • daemon/test/single-instance.test.ts
  • daemon/test/tailscale-localapi.test.ts
  • daemon/test/tunnel-bootstrap.test.ts
  • docs/tailscale-acl-example.md
  • scripts/gen-accessors-tool/Package.swift
  • scripts/gen-accessors-tool/Sources/GenAccessors/main.swift
  • scripts/gen-accessors.test.ts
  • scripts/gen-accessors.ts
  • sections/preamble.md
  • templates/Bridges.swift.template
  • templates/DebugBridgeManager.swift.template
  • templates/DebugBridgeTouch.h.template
  • templates/DebugBridgeTouch.m.template
  • templates/DebugBridgeWiring.swift.template
  • templates/DebugOverlay.swift.template
  • templates/Package.swift.template
  • templates/StateAccessor.swift.template
  • templates/StateServer.swift.template

See and control which skills your people use

Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.

30 minutes. No commitment.

SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF

More engineering skills and plugins

See all