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 description with excellent specificity and distinctiveness, clearly naming the tool (Sysinternals Autoruns), the domain (malware persistence), and the specific areas of analysis (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 over others.
Suggestions
Add a 'Use when...' clause such as 'Use when investigating malware persistence, analyzing autoruns output, checking startup entries, or performing Windows forensic analysis.'
| 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.' | 3 / 3 |
Completeness | Clearly answers 'what' (identify and analyze malware persistence mechanisms using Autoruns across specific locations), but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Autoruns', 'malware', 'persistence', 'registry keys', 'scheduled tasks', 'services', 'drivers', 'startup locations', 'Windows'. These cover the terms a user investigating malware persistence would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific tool (Sysinternals Autoruns), the specific domain (malware persistence mechanisms), and the specific platform (Windows). 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 decent heuristic flagging, but it falls short of its own promises — the overview mentions baseline diffing, VirusTotal integration, and offline analysis, none of which are implemented. The workflow is incomplete (only 'Step 1' exists), lacks validation checkpoints critical for security analysis, and includes boilerplate sections ('When to Use') that waste tokens without adding value.
Suggestions
Complete the workflow by adding steps for baseline comparison (using Autoruns -z and diff), VirusTotal hash checking, and a decision/remediation step with explicit validation checkpoints.
Remove the generic 'When to Use' section entirely — it's circular and adds no actionable information Claude doesn't already know.
Replace the 'Validation Criteria' bullet list with concrete verification commands or code (e.g., a script that validates scan completeness by checking category coverage).
Add the VirusTotal integration code and offline analysis examples promised in the overview, or remove those claims from the overview to match actual content.
| 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 despite mentioning these in the overview). The CLI flags are embedded in the script but not explained independently, and key promised capabilities are left unimplemented. | 2 / 3 |
Workflow Clarity | Despite being labeled 'Step 1,' there are no subsequent steps — no baseline comparison workflow, no VirusTotal checking step, no remediation or verification steps. For a security analysis workflow involving potentially destructive decisions (removing persistence mechanisms), there are no validation checkpoints or feedback loops. The 'Validation Criteria' section lists desired outcomes but provides no mechanism to verify them. | 1 / 3 |
Progressive Disclosure | The document has reasonable section structure and external references at the bottom. However, there are no bundle files to offload detailed content to, and the skill tries to be both an overview and a detailed guide without succeeding at either. The single monolithic script could benefit from being split or having advanced topics referenced separately. | 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
0f429d0
- 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.