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 makifbaysal/tasktrooper --skill desktop-and-local-ipc-securitygit clone --depth 1 https://github.com/makifbaysal/tasktrooperWrote 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/makifbaysal/tasktrooper/desktop-and-local-ipc-security)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/desktop-and-local-ipc-security"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/desktop-and-local-ipc-security/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/makifbaysal/tasktrooper/desktop-and-local-ipc-security"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/desktop-and-local-ipc-security.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 | $0.00078 | $0.02262 |
| Opus 5.5 | $0.00031 | $0.00905 |
| Sonnet 5.5 | $0.00016 | $0.00452 |
| Haiku 4.5 | $0.00008 | $0.00226 |
Grade A, and why
desktop-and-local-ipc-security 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 10d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Desktop and Local IPC Security
Overview
A desktop app's attackers are not "the internet" in general. They are a web page open in the user's browser (which can send requests to 127.0.0.1), another app or OS user on the same machine, a document or archive the user opened, a link the user clicked, and remote content loaded into a webview. Each reaches the app through a different door: a loopback port, a socket, a URL scheme, an IPC channel, a file.
Core principle: name the attacker's starting position, then show the check that stops it at that door. A process name, a path, a port number or a claimed sender field is not authentication — an OS peer credential, a code-signature check, or an unguessable per-launch token is.
1. Loopback HTTP and WebSocket Servers
Any web page can send requests to http://127.0.0.1:<port>. "Simple" requests — a form POST, text/plain bodies, GET with side effects — need no CORS preflight and still execute; DNS rebinding lets a page on attacker.example read responses once its name resolves to 127.0.0.1; a WebSocket upgrade carries no CORS check at all.
// ❌ a local API that runs agent tasks, open to every page in every browser on the machine
mux.HandleFunc("/api/run", runHandler)
http.ListenAndServe("127.0.0.1:"+port, mux)
// ✅ a per-launch random token in a header (pages cannot read or guess it, and it is never a cookie),
// plus a Host check that defeats DNS rebinding for the routes that need no token
func guard(next http.Handler, token string, port string) http.Handler {
allowed := map[string]bool{"127.0.0.1:" + port: true, "localhost:" + port: true}
return http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
if !allowed[r.Host] { http.Error(w, "bad host", http.StatusForbidden); return }
if subtle.ConstantTimeCompare([]byte(r.Header.Get("Authorization")), []byte("Bearer "+token)) != 1 {
http.Error(w, "unauthorized", http.StatusUnauthorized); return
}
next.ServeHTTP(w, r)
})
}
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.
- 10d ago First seen · 122 lines · 78 tokens per session scan A 53805ea97015
desktop-and-local-ipc-security is a skill published in the GitHub repository makifbaysal/tasktrooper (118 stars, last pushed 4d ago), licensed Apache-2.0. It adds 78 tokens to every session and 2,262 once invoked, about $0.0003 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 2026-10-15.
Other skills, from other repositories
cdf-simulation
Component-owned guidance for CDF Simulation requests submitted directly or through Airflow-triggered DIG Flow Catalog prompts — golden THT board, THT pin-geometry variation, good/clean SMT images, structural pose defects, and solder texture defects, from a board USD. Turns one matched prompt into one validated…
amc-run-rtsp-calibration
Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras; VIOS records clips, AMC ingests them, then runs calibration.
deepstream-generate-pipeline
Build DeepStream GStreamer pipelines interactively. Use when the user asks about pipelines for video/image inference, detection, tracking, or streaming — including natural phrases like 'pipeline to infer on image', 'run inference on video', 'detect objects in stream', 'save inference output', 'deepstream pipeline'…
doca-flow
DOCA Flow packet steering on NVIDIA NICs/DPUs, linked into a C application: match/action pipes, ports, representors, forwarding, hairpin, counters. Trigger on packet steering, classifier, rule-matching, representor, hairpin or 5-tuple-to-queue questions even when "DOCA Flow" is not named. Remote or non-C++ control…
jetson-derive-carrier
Bootstrap a custom carrier board by forking carrier files and scaffolding a DT overlay from the reference devkit. Use after jetson-init-source; not for module-level or kernel-DTB changes.
isaac-mission-control-showcase
Run and validate an end-to-end Mission Control showcase with a locally installed Isaac Sim launched in its GUI window, driven through the isaac-sim-remote Python server, with Nova Carter SIL. Use for demos, showcase replays, Mission Control driving a simulated robot, or diagnosing the integrated small-warehouse…