CtrlK
BlogDocsLog inGet started
Tessl Logo

dcsync

Abuse replication rights (DS-Replication-Get-Changes + GetChangesAll) to dump krbtgt and arbitrary user NT hashes from a DC.

65

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./packages/decepticon/decepticon/skills/standard/ad/dcsync/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

83%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.

The playbook is exceptionally actionable and token-efficient, with copy-paste commands across Impacket, Mimikatz, and Defender tooling. Its main gap is the absence of an explicit verification step after the dump, which caps workflow clarity for a batch credential-extraction operation.

Suggestions

Add a validation checkpoint after the dump — e.g. 'Verify: grep the .ntds file for krbtgt and confirm the hash is 32 hex chars; re-run with -just-dc-user krbtgt if missing.'

Add a brief failure/feedback loop note for when 4662 is detected or secretsdump returns empty (e.g. confirm replication rights, try Kerberos auth).

Consider splitting the detection-signature and Defender-remediation sections into a referenced file to push progressive disclosure toward 5.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it never explains what AD, Kerberos, or replication are, and the brief framing line ('DCSync is not a vulnerability…') earns its place by clarifying scope without padding.

5 / 5

Actionability

Commands are copy-paste ready and cover the common cases: secretsdump.py with exact auth variants (-just-dc, -just-dc-user, -hashes, -k), mimikatz lsadump::dcsync, ticketer.py golden-ticket generation, and PowerShell remediation.

5 / 5

Workflow Clarity

Sections are numbered 1–6 with a clear sequence (identify → execute → outputs → high-value targets → golden ticket → promote), but a credential-dump is a batch operation with no validate/verify checkpoint confirming hashes were extracted and are usable, so per the guideline workflow clarity is capped at 3.

3 / 5

Progressive Disclosure

Content is self-contained with clear section headers and no nested references; structure is good and appropriate, though at ~120 lines with no external reference split it sits just below the cleanly-modular 5 anchor.

4 / 5

Total

17

/

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.

The description is highly specific and distinctive, naming the exact ACLs and high-value targets, but it omits any explicit 'when to use this' trigger guidance, which caps completeness at 3. Adding a 'Use when...' clause would lift the weakest dimension.

Suggestions

Append an explicit trigger clause, e.g. 'Use when you have replication rights on a domain controller and need to dump krbtgt or user NT hashes via DCSync.'

Surface the natural term 'dcsync' directly in the description (not only in metadata.when_to_use) to strengthen trigger-term coverage.

Consider listing the primary tool (secretsdump.py) in the description to improve discoverability for users who phrase requests around the tool.

DimensionReasoningScore

Specificity

Names multiple concrete actions and targets — 'Abuse replication rights (DS-Replication-Get-Changes + GetChangesAll)' and 'dump krbtgt and arbitrary user NT hashes from a DC' — with comprehensive, specific coverage rather than generic language.

5 / 5

Completeness

It clearly answers 'what' (abuse replication rights to dump hashes) but provides no explicit 'when to use it' / 'Use when...' clause, so per the guideline a missing trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Includes strong natural keywords a practitioner would say ('replication rights', 'krbtgt', 'NT hashes', 'dump'), but is missing some common synonyms or the standalone 'dcsync' trigger term that lives only in metadata, so coverage is good but not fully comprehensive.

4 / 5

Distinctiveness Conflict Risk

The DCSync/krbtgt/NT-hash-from-DC niche is highly specific with distinct triggers and minimal overlap risk against other skills.

5 / 5

Total

17

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
PurpleAILAB/Decepticon
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.