analyzing-uefi-bootkit-persistence

Analyzes UEFI bootkit persistence (SPI flash implants, ESP modifications, Secure Boot bypass, UEFI variable manipulation) using chipsec for firmware integrity verification, detecting known families like BlackLotus, LoJax, and MoonBounce. Use for UEFI malware analysis, firmware persistence investigation, or Secure Boot bypass detection.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

65%

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

The content is highly actionable with concrete, executable commands across a clear seven-step workflow, but it is let down by verbosity (a large sample report and concept re-explanation) and by failing to signal its existing bundle files. Adding validation checkpoints and linking the reference/script files would lift the weaker dimensions.

Suggestions

Replace the full ~77-line sample output report with a short template plus a pointer, and trim the Key Concepts entries that restate what Secure Boot and chipsec are, to improve conciseness.

Insert explicit validation checkpoints between steps (e.g. 'Confirm sha256sum matches before proceeding; if mismatch, re-dump') to add the validate->fix->retry feedback loops expected for destructive firmware operations.

Reference the existing bundle files from the body — link references/api-reference.md for the full command catalog and scripts/agent.py for automation — so progressive disclosure is signaled rather than hidden.

Dimension	Reasoning	Score
Conciseness	The body is mostly action-oriented commands, but the 'Key Concepts' table re-explains things Claude knows (what Secure Boot/chipsec are) and the ~77-line sample output report (lines 292-369) is verbose padding that could be trimmed. It is not a 3 because several sections do not earn their tokens, and not a 1 because the bulk is concrete guidance rather than conceptual prose.	2 / 3
Actionability	Every step ships copy-paste-ready, executable commands with specifics — exact chipsec modules, full UEFI variable GUIDs, registry paths, and YARA invocations — matching the top anchor for fully executable guidance.	3 / 3
Workflow Clarity	Seven clearly sequenced steps exist, but for destructive/risky firmware operations there are no explicit validate->fix->retry checkpoints gating the next step; verification (e.g. sha256sum, integrity checks) appears as a step rather than a feedback loop, so per the rubric feedback-loop rule workflow clarity is capped at 2.	2 / 3
Progressive Disclosure	Bundle files (references/api-reference.md, scripts/agent.py) exist but are never referenced or signaled from the body, and content that should be split out — the full sample report and a command catalog duplicated with api-reference.md — is inline, giving structure but not the well-signaled one-level-deep references of the top anchor.	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.

The description is specific, well-triggered, and complete, naming concrete capabilities and an explicit 'Use for' clause tied to natural analyst language. It is clearly distinguishable from generic malware-analysis skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'SPI flash implants, ESP modifications, Secure Boot bypass, UEFI variable manipulation' plus 'firmware integrity verification' and 'detecting known families like BlackLotus, LoJax, and MoonBounce' — matching the top anchor for specific concrete actions.	3 / 3
Completeness	Explicitly answers what ('Analyzes UEFI bootkit persistence ... using chipsec for firmware integrity verification') and when via an explicit 'Use for UEFI malware analysis, firmware persistence investigation, or Secure Boot bypass detection' trigger, satisfying both halves of the top anchor.	3 / 3
Trigger Term Quality	Includes natural terms a security analyst would say — 'UEFI malware analysis', 'firmware persistence investigation', 'Secure Boot bypass detection' — with good coverage rather than only opaque jargon; not a 2 because common variations are well represented.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear UEFI-bootkit niche with distinct triggers and named malware families, making it unlikely to fire for unrelated skills; not a 2 because the scope is sharply bounded to firmware-level persistence.	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-uefi-bootkit-persistence/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.