hunting-scheduled-task-abuse

hunting-scheduled-task-abuse is a skill for Claude Code, Codex from meltedinhex/analyst-ai-pack. It costs 63 tokens per session (691 once invoked), scanned A, original, Apache-2.0.

A security-hunting guide for finding malicious Windows Scheduled Tasks, which can run programs automatically at login, startup, or set times to keep an attacker on a machine.

In plain words
What is it for?
Use it to analyze task-registration and process telemetry, find encoded commands or scripts from suspicious locations, and turn confirmed patterns into Sigma detection rules.
Why use it?
It helps distinguish suspicious persistence from normal task creation by examining the task's action, trigger, hiding settings, author, and file path.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to analyze task-registration and process telemetry, find encoded commands or scripts from suspicious locations, and turn confirmed patterns into Sigma detection rules.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/meltedinhex/analyst-ai-pack/hunting-scheduled-task-abuse
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.

Any agent
npx skills add meltedinhex/analyst-ai-pack --skill hunting-scheduled-task-abuse
Clone the repo
git clone --depth 1 https://github.com/meltedinhex/analyst-ai-pack

Made for: Claude Code, Codex.

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 hunting-scheduled-task-abuse

README.md
[![agentmods](https://agentmods.dev/badge/skills/meltedinhex/analyst-ai-pack/hunting-scheduled-task-abuse/github.svg)](https://agentmods.dev/skills/meltedinhex/analyst-ai-pack/hunting-scheduled-task-abuse)
Your own site
<a href="https://agentmods.dev/skills/meltedinhex/analyst-ai-pack/hunting-scheduled-task-abuse"><img src="https://agentmods.dev/badge/skills/meltedinhex/analyst-ai-pack/hunting-scheduled-task-abuse/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.

agentmods 80×15 button for hunting-scheduled-task-abuse

Your own site · 80×15
<a href="https://agentmods.dev/skills/meltedinhex/analyst-ai-pack/hunting-scheduled-task-abuse"><img src="https://agentmods.dev/badge/skills/meltedinhex/analyst-ai-pack/hunting-scheduled-task-abuse.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 691 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00063 $0.00691
Opus 5 $0.00032 $0.00345
Sonnet 5 $0.00013 $0.00138
Haiku 4.5 $0.00006 $0.00069

Measured 8d ago against content hash 3c5caf5a86e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

hunting-scheduled-task-abuse 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/analyst.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/hunting-scheduled-task-abuse/SKILL.md · 87 lines

What it actually says

Hunting Scheduled Task Abuse

When to Use

  • You have task-registration events (4698) and/or schtasks.exe/at.exe process telemetry and want to detect persistence via malicious scheduled tasks.
  • You are investigating tasks that run scripts, encoded commands, or binaries from suspicious paths.

Do not use this to alert on all task creation — administration creates tasks routinely. Hunt on the action (script hosts, encoded commands, temp paths) and trigger context.

Prerequisites

  • Event ID 4698 (task registered) and/or process-creation telemetry for schtasks/at.

Workflow

Step 1: Hunt suspicious task actions

python scripts/analyst.py hunt events.csv

Flags tasks whose action runs powershell -enc, mshta, wscript/cscript, cmd /c, or binaries from %TEMP%/%APPDATA%/Public, and schtasks /create command lines with the same.

Step 2: Assess triggers and hiding

Note logon/onstart triggers, very frequent intervals, and tasks hidden via Hidden flag or SD manipulation.

Step 3: Confirm

Distinguish legitimate software tasks from intrusion by author, path, and action content.

Step 4: Operationalize

Write a Sigma rule for task actions invoking script hosts or encoded commands.

Validation

  • Flags require a suspicious action/path, not task creation alone.
  • schtasks /create and 4698 registrations are both covered.
  • Findings map to ATT&CK T1053.005.

Pitfalls

  • Legitimate updater tasks (browsers, vendors) creating many tasks.
  • Tasks created via direct XML drop bypassing schtasks.exe telemetry.
  • Encoded commands hiding the true action.

References

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 87 lines · 63 tokens per session scan A 3c5caf5a86e1

Subscribe to this mod's changes

hunting-scheduled-task-abuse is a skill published in the GitHub repository meltedinhex/analyst-ai-pack (22 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 63 tokens to every session and 691 once invoked, about $0.0003 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 2026-09-03.

Related

Other skills, from other repositories

hunting-for-registry-run-key-persistence

Use when detect MITRE ATT&CK T1547.001 registry Run key persistence by analyzing Sysmon Event ID 13 logs and registry queries to identify malicious auto-start entries. Use when detecting mitre att&ck t1547.001 registry run key persistence by analyzing.

oyi77/1ai-skills · 66 tokens

analyzing-cobalt-strike-beacon-configuration

Extract and analyze Cobalt Strike beacon configuration from PE files and memory dumps to identify C2 infrastructure, malleable profiles, and operator tradecraft.

mukul975/Anthropic-Cybersecurity-Skills · 42 tokens

analyzing-golang-malware-with-ghidra

Reverse engineer Go-compiled malware in Ghidra by parsing Go buildinfo and pclntab structures, recovering stripped/obfuscated function names (e.g. via GoResolver), and extracting embedded module/dependency strings and types from Go binaries. Use when analyzing a Go-language malware sample, deobfuscating a…

mukul975/Anthropic-Cybersecurity-Skills · 95 tokens

analyzing-malware-persistence-with-autoruns

Use Sysinternals Autoruns to systematically enumerate and analyze malware persistence mechanisms across Windows registry run keys, scheduled tasks, services, drivers, and startup locations. Use when hunting for persistence during Windows incident response, triaging a compromised endpoint, or validating that malware…

mukul975/Anthropic-Cybersecurity-Skills · 74 tokens

analyzing-malicious-pdf-with-peepdf

Perform static analysis of malicious PDF documents using peepdf, pdfid, and pdf-parser to extract embedded JavaScript, shellcode, and suspicious objects. Use when triaging a suspicious PDF attachment from a phishing email, analyzing a PDF-based exploit document, or building detection signatures for weaponized PDF…

mukul975/Anthropic-Cybersecurity-Skills · 73 tokens

detecting-email-forwarding-rules-attack

Detect malicious email forwarding rules created by adversaries to maintain persistent access to email communications for intelligence collection and BEC attacks.

adriannoes/awesome-agentic-ai · 34 tokens