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.

64

Quality

77%

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

87%

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

A tight, highly actionable offensive playbook with executable commands and clean single-file organization; the only gap is the absence of explicit validation checkpoints for a batch/destructive hash-dumping operation.

Suggestions

Add an explicit verification step after the dump (e.g., confirm krbtgt usability by forging a TGT and validating access before promoting the credential) to close the validation loop for this batch operation.

Optionally split the blue-team remediation/detection sections into a referenced file if the skill should stay purely offensive-scoped.

DimensionReasoningScore

Conciseness

Expert-voiced and lean throughout — the one framing sentence reframes DCSync as a misused legitimate feature (non-obvious), and every section (queries, commands, output formats, value table, promotion, OPSEC, detection, CVSS, remediation) earns its place with no explanation of basic concepts.

3 / 3

Actionability

Fully executable guidance: real secretsdump.py invocations with flags, mimikatz commands, ticketer.py/psexec.py chaining, BloodHound Cypher and kg_query snippets, and spelled-out output file formats — copy-paste ready, not pseudocode.

3 / 3

Workflow Clarity

A clear 6-step sequence exists (identify → execute → outputs → grab secrets → golden ticket → promote), but for a batch secret-dumping operation there is no explicit validation checkpoint confirming success before moving on, capping workflow clarity at 2 per the destructive/batch-operations guideline.

2 / 3

Progressive Disclosure

No bundle files exist; the single self-contained file uses clear section headers and stays one level deep with no nested references, appropriate for a focused playbook that needs no external material.

3 / 3

Total

11

/

12

Passed

Description

67%

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 precise, distinctive offensive-AD description that clearly conveys what it does, but it relies on metadata.when_to_use rather than an explicit in-description 'Use when' trigger clause, leaving completeness and trigger-term quality at the mid level.

Suggestions

Append an explicit 'Use when...' clause to the description naming natural trigger phrases (e.g., 'Use when dumping NTDS/krbtgt hashes, forging golden tickets, or checking who holds DCSync rights').

Fold common phrasings such as 'NTDS dump' and 'golden ticket' into the trigger terms so they appear in the description itself.

DimensionReasoningScore

Specificity

Names the specific ACLs (DS-Replication-Get-Changes + GetChangesAll) and two concrete extraction targets (krbtgt, arbitrary user NT hashes) from a DC — multiple specific concrete actions, not just a domain label.

3 / 3

Completeness

The description clearly states what the skill does but has no explicit 'Use when...' clause in the description field; trigger guidance lives only in metadata, so per the guideline completeness is capped at 2.

2 / 3

Trigger Term Quality

metadata.when_to_use provides relevant keywords (dcsync, secretsdump, krbtgt, nt hash dump) but mixes in technical jargon and omits common natural phrasings (NTDS dump, golden ticket), and the terms are not woven into the description itself.

2 / 3

Distinctiveness Conflict Risk

A narrow AD-offensive niche (replication-right abuse for krbtgt/NT-hash dumping) with distinct technical triggers, very unlikely to fire for unrelated skills.

3 / 3

Total

10

/

12

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.