agentmods.dev

desktop-agent

desktop-agent is an agent for Claude Code from TyrusRC/praetor. It costs 40 tokens per session (877 once invoked), scanned A, original, Apache-2.0.

A security-testing worker for desktop applications built with Electron, Tauri, WebView2, NW.js, or CEF. It inspects the application binary and its packaged files, then helps test its internal messaging and update mechanisms.

In plain words
What is it for?
Use it to extract and rescan Electron packages, inspect security settings and embedded versions, enumerate desktop message handlers, prepare DevTools and proxy tests, and review update endpoints and signatures.
Why use it?
Desktop apps can hide source files, secrets, unsafe message handlers, or weak update protections inside their package. This agent gathers those areas for focused review without testing unrelated web or mobile targets.

Agent for Claude Code

not rated 5 15d ago A scan 40 tokens original Apache-2.0
View the source file TyrusRC/praetor
Install

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.

agentmods
npx agentmods add agents/tyrusrc/praetor/desktop-agent
Clone the repo
git clone --depth 1 https://github.com/TyrusRC/praetor

Made for: Claude Code.

Wrote 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.

agentmods badge for desktop-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/tyrusrc/praetor/desktop-agent.svg)](https://agentmods.dev/agents/tyrusrc/praetor/desktop-agent)
Your own site
<a href="https://agentmods.dev/agents/tyrusrc/praetor/desktop-agent"><img src="https://agentmods.dev/badge/agents/tyrusrc/praetor/desktop-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 877 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00040 $0.00877
Opus 5 $0.00020 $0.00439
Sonnet 5 $0.00008 $0.00175
Haiku 4.5 $0.00004 $0.00088

Measured 5d ago against content hash 560621e1176d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

desktop-agent 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 5d 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.

.claude/agents/desktop-agent.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

desktop-agent

When to dispatch

Operator hands a desktop binary path, or the target intel marks kind: desktop. Frameworks: Electron, Tauri, WebView2, NW.js, CEF. Single-binary scope. 1-per-binary (no parallel runs on same file — repack races).

NOT for: web targets, mobile apps, mobile webviews (those have their own agents).

Capabilities

  • ASAR extract / repack via npx asar
  • Electron Fuses read via npx @electron/fuses
  • Electronegativity static scan
  • Secret sweep via existing run_trufflehog + run_gitleaks on the extracted directory
  • CVE mapping via kev_epss_enrich from process.versions.electron / process.versions.chrome
  • Burp proxy launch helper — emits <bin> --proxy-server=http://127.0.0.1:8080 command for the operator (cannot launch GUI apps headlessly)
  • Match-replace rule proposals for auto-update MITM via match_replace tool
  • IPC-handler enumeration + DevTools fuzz payload generation (operator pastes in renderer console)
  • Tauri auto-update channel decoder (W9): parse tauri.conf.json updater.endpoints + updater.pubkey; emit MITM match-replace plans for each endpoint; probe for missing Sigstore signature bundles (<binary>.sig / <binary>.pem); flag stale TUF timestamp metadata as freeze-attack surface.

Out of scope

  • Cannot drive native UI (no AppleScript / pywinauto integration — manual operator step).
  • Cannot launch GUI binaries headlessly. Operator launches, agent inspects.
  • No mobile (mobile-dynamic-agent owns that).
  • No CloakBrowser usage — desktop is binary inspection, not web automation.

Inputs

  • binary_path (required) — absolute path to .app / .exe / .AppImage
  • framework_hint (optional) — electron | tauri | webview2 | auto
  • workdir (optional) — scratch dir for extraction (default .burp-intel/<domain>/desktop/)

Workflow

  1. Detect framework (file magic + bundled artifacts: resources/app.asar = Electron; tauri.conf.json = Tauri; WebView2Loader.dll = WebView2).
  2. Extract ASAR (Electron) or read Tauri config (Tauri) or locate WebView2 host EXE.
  3. Run KB desktop_electron static contexts via shell — each context's detect field is the operator-runnable command.
  4. Run electronegativity, run_trufflehog, run_gitleaks; collect findings.
  5. Read Electron Fuses, map version to CVEs via kev_epss_enrich.
  6. Emit save_finding calls per confirmed issue with evidence.file_path + evidence.line_number and chain_with[] where required (NEVER-SUBMIT alone: ASAR disclosure, missing will-navigate, missing CSP).
  7. Hand back to operator: list of dynamic probes that need GUI interaction (auto-update MITM walkthrough, deep-link triggers, shell.openExternal flow targeting).

Read the full file on GitHub · 63 lines

Changes

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.

  1. 5d ago First seen · 63 lines · 40 tokens per session scan A 560621e1176d

Subscribe to this mod's changes

desktop-agent is an agent published in the GitHub repository TyrusRC/praetor (5 stars, last pushed 15d ago), licensed Apache-2.0. It adds 40 tokens to every session and 877 once invoked, about $0.0002 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 2026-08-31.

Securityburpsuiteclaude-codeclaude-skillspentestpentest-toolpentesting
Related

Other agents, from other repositories

senior-pentester

20+ year offensive security reviewer. Receives one logical firewall's normalized ruleset (already through deterministic detectors) and flags semantic concerns detectors can't catch — business-logic gaps, trust-boundary violations, unusual service combos. 2-4 instances dispatched in parallel during /launch.

transilienceai/communitytools · 62 tokens

ciso-reviewer

Business-impact gate. Adjusts severity based on asset criticality, engagement regulatory overlay, and compensating controls. Does NOT veto findings.

transilienceai/communitytools · 32 tokens

citation-verifier

Deterministic (not LLM). Greps every finding's quoted rule text in its cited source file and verifies framework citation versions match the pinned set. Mismatches → quarantine.

transilienceai/communitytools · 41 tokens

cto-reviewer

Technical truth gate. Re-derives each finding's claim from the parsed rule AST and returns yes/no/uncertain. Uncertain findings route to held/ for human reviewer.

transilienceai/communitytools · 40 tokens

qa-reviewer

Editorial gate. Final pass on phrasing, framework-citation-version accuracy, cross-finding consistency. Flags (never blocks) findings that need author attention.

transilienceai/communitytools · 35 tokens

agent-dynamic-tester

Role brief for the dynamic-tester agent — performs runtime / negative testing (Perform / Test methods) against an authorized running instance for PCI SSS v2.0 dynamic Test Requirements, capturing dynamicobservation evidence. When no running instance is authorized, the requirement is REQUIRESMANUALREVIEW, never a faked…

transilienceai/communitytools · 73 tokens