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 autostart entries have been fully identified and removed.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

70%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is actionable with executable code and accurate technical detail, but the body functions as a monolithic self-contained script rather than an overview that leverages the well-structured bundle files, and the workflow lacks an explicit validation feedback loop.

Suggestions

Replace or supplement the inline scanning script with a pointer to scripts/agent.py and references/api-reference.md so the SKILL.md body stays a lean overview that progressively discloses detail.

Add a numbered multi-step workflow (collect baseline -> scan -> compare baseline -> triage flagged entries -> validate removal) with an explicit validate-then-retry checkpoint, since this is a batch operation over many ASEP entries.

Reference the bundle files explicitly in the body (e.g., link references/api-reference.md for flag/CSV-column details and assets/template.md for reporting) so the one-level-deep navigation is clearly signaled.

Dimension	Reasoning	Score
Conciseness	The body is largely lean (concise overview, prerequisites, a single working script), but the embedded Python script and Overview restate ASEP categories and suspicious-indicator logic that are duplicated in references/api-reference.md, adding tokens Claude largely could infer or find in bundled files.	2 / 3
Actionability	Provides a complete, executable autorunsc invocation ('-a * -c -h -s -nobanner') and a working parse_and_flag script with concrete flagging logic for unsigned binaries, suspicious paths, and LOLBins — copy-paste ready.	3 / 3
Workflow Clarity	A single 'Step 1: Automated Persistence Scanning' is presented without an explicit validate-fix-retry checkpoint; while Validation Criteria are listed afterward, there is no feedback loop tying a failed/flagged result back to a remediation step, capping clarity at 2 for this batch analysis operation.	2 / 3
Progressive Disclosure	Bundle files exist (references/api-reference.md, standards.md, workflows.md; scripts/agent.py; assets/template.md) and are well-organized, but the SKILL.md body never signals or links to any of them, so navigation to the deeper material is unclear and the inline script duplicates content that lives in the bundle.	2 / 3
	Total	9 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that concretely states capabilities and provides explicit trigger conditions tied to realistic incident-response scenarios. It is specific, distinctive, and avoids verbosity or fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across specific targets: 'enumerate and analyze malware persistence mechanisms across Windows registry run keys, scheduled tasks, services, drivers, and startup locations', naming distinct ASEP categories rather than vague verbs.	3 / 3
Completeness	Explicitly answers both what (enumerate/analyze persistence across listed locations) and when via a clear 'Use when hunting for persistence during Windows incident response, triaging a compromised endpoint, or validating that malware autostart entries have been fully identified and removed.'	3 / 3
Trigger Term Quality	Covers natural terms an analyst would say — 'hunting for persistence', 'Windows incident response', 'triaging a compromised endpoint', 'malware autostart entries' — giving good coverage of phrasings users actually invoke.	3 / 3
Distinctiveness Conflict Risk	The niche is sharply bounded to Autoruns-based Windows persistence enumeration; triggers reference hunting, triage, and autostart validation, making overlap with unrelated skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: mukul975/Anthropic-Cybersecurity-Skills
Path: skills/analyzing-malware-persistence-with-autoruns/SKILL.md
Commit: e612f49

Reviewed: about 10 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.