analyzing-malware-persistence-with-autoruns
Use Sysinternals Autoruns to systematically identify and analyze malware persistence mechanisms across registry keys, scheduled tasks, services, drivers, and startup locations on Windows systems.
53
60%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/analyzing-malware-persistence-with-autoruns/SKILL.mdQuality
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong, specific description that clearly identifies the tool (Sysinternals Autoruns), the domain (malware persistence analysis), and the specific areas covered (registry keys, scheduled tasks, services, drivers, startup locations). Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The rich set of domain-specific trigger terms makes it highly discoverable for relevant queries.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about malware persistence, autoruns analysis, suspicious startup entries, or investigating Windows persistence mechanisms.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and locations: 'identify and analyze malware persistence mechanisms across registry keys, scheduled tasks, services, drivers, and startup locations on Windows systems.' This is highly specific about what the skill does. | 3 / 3 |
Completeness | Clearly answers 'what does this do' (identify and analyze malware persistence mechanisms using Autoruns across multiple locations), but lacks an explicit 'Use when...' clause or equivalent trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Autoruns', 'malware', 'persistence mechanisms', 'registry keys', 'scheduled tasks', 'services', 'drivers', 'startup locations', 'Windows', 'Sysinternals'. These cover the terms a user investigating malware persistence would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct niche: specifically about Sysinternals Autoruns for malware persistence analysis on Windows. The combination of the specific tool (Autoruns), the specific task (persistence mechanism analysis), and the specific platform (Windows) makes it highly unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
37%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides a useful Python script for automated Autoruns scanning with good suspicious-entry heuristics, but it significantly under-delivers on its stated scope. The overview promises baseline diffing, VirusTotal integration, and offline forensic analysis, yet the workflow only contains a single step covering basic scanning. The 'When to Use' and 'Validation Criteria' sections are generic filler that waste tokens without adding actionable guidance.
Suggestions
Add concrete workflow steps for baseline creation, baseline comparison (diffing), VirusTotal hash lookup, and offline analysis with the -z flag—each with executable code or commands and validation checkpoints.
Remove the generic 'When to Use' section entirely, as it adds no information Claude couldn't infer.
Replace the 'Validation Criteria' bullet list with actual verification commands or code that confirm each criterion is met (e.g., a script that checks all 18+ ASEP categories were scanned).
Add a quick-reference section showing key autorunsc CLI invocations (baseline export, comparison, offline mode) as standalone copy-paste commands before the full Python script.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The overview is reasonably dense with useful technical detail, but the 'When to Use' section is generic boilerplate that adds no value (e.g., 'When investigating security incidents that require analyzing malware persistence with autoruns' is circular). The 'Validation Criteria' section is also vague filler. | 2 / 3 |
Actionability | The Python script is executable and concrete, which is good. However, the skill only covers Step 1 of what should be a multi-step workflow (no baseline comparison code, no VirusTotal integration code, no offline analysis examples despite mentioning these in the overview). The CLI flags are embedded in code but not explained as standalone commands. | 2 / 3 |
Workflow Clarity | Despite being labeled 'Step 1,' there are no subsequent steps. The workflow lacks baseline creation, comparison diffing, VirusTotal checking, and offline analysis—all mentioned in the overview. There are no validation checkpoints or feedback loops for what is essentially a security-critical investigative process. The 'Validation Criteria' section lists desired outcomes but provides no mechanism to verify them. | 1 / 3 |
Progressive Disclosure | The content has reasonable section structure and external references at the bottom. However, there are no bundle files to support progressive disclosure, and the skill promises capabilities (baseline comparison, VirusTotal integration, offline analysis) that are neither implemented inline nor referenced in separate files. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- mukul975/Anthropic-Cybersecurity-Skills
- Commit
0445030
- Reviewed
Table of Contents
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.