CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

reverser-ransomware-analysis

Ransomware family identification and analysis — encryption scheme identification, key recovery techniques, ransom note parsing, shadow copy/recovery inhibition analysis, decryptor availability check, and IOC extraction for common ransomware families.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./packages/decepticon/decepticon/skills/standard/reverser/ransomware-analysis/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%Weight 40%Scale 1-5

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

A dense, command-first analyst field guide covering the full workflow (family ID, crypto analysis, key recovery, recovery inhibition, IOC extraction) with mostly copy-paste-ready code. Main weaknesses: a systematic grep -E '\|' alternation bug that breaks most triage commands, no validation checkpoints before destructive/batch steps like running decryptors, and a fully monolithic structure with no progressive disclosure.

Suggestions

Fix the grep alternation bug: under `grep -E`, '\|' matches a literal pipe, so replace `grep -iE 'lockbit\|revil\|conti'` with plain `|` (as the Quick Reference section already does) so the strings-based triage commands in sections 1–6 actually match.

Add validation checkpoints before destructive/batch operations: e.g., 'Test the decryptor on a single copied file and verify the output opens before batch-decrypting' and 'Confirm shadow copies exist via `vssadmin list shadows` before mounting for recovery'.

Move the lookup tables (MITRE ATT&CK mapping, tools, detection signatures, edge cases) into a references/ file (e.g., references/tables.md) to slim the core workflow and establish progressive disclosure.

DimensionReasoningScore

Conciseness

The body is command-dense with almost no conceptual padding — nearly all prose is domain-specific value (mutex names, crypto patterns, trailer layouts) rather than concepts Claude already knows. It falls short of 5 because NoMoreRansom/Emsisoft decryptor URLs appear three times (Quick Reference, Technique 5, Tools table) and the Tools/Detection tables partially duplicate inline content.

4 / 5

Actionability

Mostly executable, copy-paste-ready guidance: complete Python heredocs for entropy analysis, import-table enumeration, and IOC regex extraction, plus concrete vssadmin/strings commands. It is not fully executable (5) because the pervasive `grep -iE 'lockbit\|revil\|...'` patterns use '\|' which matches a literal pipe under ERE — those triage commands silently return nothing (the Quick Reference already uses the correct plain '|') — and `yara -r /opt/yara-rules/ransomware/` assumes an unverified environment path.

4 / 5

Workflow Clarity

A clear sequence exists (numbered sections 1–6 from family identification through IOC extraction) and the Decision Gate adds explicit IF-branches. However, there are no validation checkpoints for destructive/batch operations — running a decryptor over victim files or mounting shadow copies — such as testing the decryptor on a single copied file and verifying output before batch decryption, so workflow clarity is capped at 3.

3 / 5

Progressive Disclosure

The skill is a single ~330-line monolithic file with no bundle files and no references signaled anywhere; peripheral lookup tables (MITRE mapping, tools, detection signatures, edge cases) that would suit separate reference files are inlined. Structure within the file is good, but content that should be separate is inline, matching the 3 anchor.

3 / 5

Total

14

/

20

Passed

Description

75%Weight 40%Scale 1-5

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, specific description that clearly names six concrete capabilities in third person, making the 'what' unambiguous. Its weaknesses are the complete absence of a 'Use when...' trigger clause (capping completeness at 3) and missing natural trigger variations such as family names and encrypted-file extensions.

Suggestions

Add an explicit trigger clause, e.g.: 'Use when the user mentions ransomware, a ransom note, encrypted or locked files (.lockbit, .revil, .blackcat), or asks about decrypting files or recovering from a ransomware incident.'

Include natural trigger synonyms users would actually say: 'decrypt my files', 'recover my files', 'locked files', and common family names (LockBit, REvil/Sodinokibi, BlackCat/ALPHV, Conti).

DimensionReasoningScore

Specificity

The description enumerates six concrete, domain-specific actions — 'encryption scheme identification', 'key recovery techniques', 'ransom note parsing', 'shadow copy/recovery inhibition analysis', 'decryptor availability check', and 'IOC extraction' — in third-person voice, comprehensively covering the ransomware analysis domain. Score 4 would require a coverage gap, and none is evident.

5 / 5

Completeness

The 'what' is clearly and explicitly stated, but the description contains no 'Use when...' clause or any equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. The when is entirely absent, not merely weakly implied.

3 / 5

Trigger Term Quality

Good natural keywords are present ('ransomware', 'ransom note', 'key recovery', 'decryptor', 'shadow copy'), but common variations users would actually say are missing: family names (LockBit, REvil, BlackCat), encrypted-file extensions (.lockbit, .revil), and phrases like 'decrypt/recover my files'. Coverage is better than 'some relevant keywords' (3) but short of comprehensive synonym/extension coverage (5).

4 / 5

Distinctiveness Conflict Risk

The description is entirely about ransomware-specific capabilities ('ransom note parsing', 'decryptor availability check', 'shadow copy/recovery inhibition analysis') with no generic verbs, giving it a clear niche with distinct triggers and minimal conflict risk. Only a marginal overlap with a generic 'malware analysis' skill is conceivable, which is not enough to drop to 4.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

PurpleAILAB/Decepticon

Path

packages/decepticon/decepticon/skills/standard/reverser/ransomware-analysis/SKILL.md

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.