CtrlK
BlogDocsLog inGet started
Tessl Logo

ad-coercer

Authentication coercion against Windows / AD — PetitPotam (MS-EFSR), PrinterBug (MS-RPRN), DFSCoerce (MS-DFSNM), ShadowCoerce (MS-FSRVP), Coercer.py meta-tool. Force a Windows machine to NTLM-authenticate to attacker, then relay or crack offline.

63

Quality

75%

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/coercer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

76%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 concise, highly actionable body with concrete commands and a clear attack workflow, weakened only by the absence of explicit validation/verification checkpoints for its destructive escalation chain.

Suggestions

Add explicit verification checkpoints in the escalation chain (e.g. confirm the relay succeeded and the certificate/TGT is valid before running secretsdump).

Consider splitting the per-vector protocol/RPC/mitigation table into a reference file to keep the core workflow leaner.

Add a feedback loop note for failed coercion (e.g. if no auth is captured, check protocol availability/patch level and retry with an alternative vector).

DimensionReasoningScore

Conciseness

Lean and efficient with no padding about what NTLM/AD is; commands and tables earn their tokens, with only minor explanatory phrasing ('All four boil down to...') that could be trimmed.

4 / 5

Actionability

Provides copy-paste-ready commands with real flags (impacket-ntlmrelayx, Coercer.py, PetitPotam.py, certipy auth, secretsdump) covering relay, capture, ADCS, and DCSync cases.

5 / 5

Workflow Clarity

A clear numbered sequence (listener -> coerce -> catch -> escalate) exists, but the operations are destructive/batch (domain compromise) and lack explicit validate-then-proceed checkpoints, which caps workflow clarity at 3 per the rubric.

3 / 5

Progressive Disclosure

Well-organized single document with clear section headers and a vector table; no bundle files exist, and while ~95 lines could be split (per-vector deep-dives, OPSEC), it remains coherent and navigable.

4 / 5

Total

16

/

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 highly specific, distinctive description that excels at naming concrete vectors and actions, but it omits any explicit 'when to use' trigger guidance, which caps completeness.

Suggestions

Add an explicit trigger clause, e.g. 'Use when forcing Windows/AD hosts to authenticate to an attacker for NTLM relay or offline cracking.'

Drop or de-emphasize the MS-* protocol codes in the description in favor of natural synonyms users actually say ('force authentication', 'coerce NTLM').

Lead with the action ('Force a Windows machine...') before the vector list so the what/when structure reads cleanly.

DimensionReasoningScore

Specificity

Names five concrete coercion vectors (PetitPotam, PrinterBug, DFSCoerce, ShadowCoerce, Coercer.py) and two concrete actions ('Force a Windows machine to NTLM-authenticate to attacker, then relay or crack offline'), giving comprehensive coverage of specific actions.

5 / 5

Completeness

The 'what' is clear and concrete, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

Includes natural tool/vuln names users say (PetitPotam, PrinterBug, DFSCoerce, ShadowCoerce, coercer, NTLM, relay) but leans on some technical jargon (MS-EFSR, MS-RPRN) and misses a few natural synonyms like 'force authentication'.

4 / 5

Distinctiveness Conflict Risk

A clear niche (Windows/AD NTLM auth coercion) with distinctive named tool/vuln triggers and minimal overlap risk with unrelated skills.

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

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.