CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

patchwork-dropping-elephant

Adversary-emulation profile for Patchwork (G0040 / Dropping Elephant / Chinastrats / MONSOON / Hangover Group / Operation Hangover), an India-linked cyber-espionage actor.

Quality

68%

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/shared/adversary-emulation/patchwork/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 content is a well-structured, actionable adversary-emulation profile with concrete CVEs, tooling, and tradecraft, but it is verbose, lacks explicit workflow validation checkpoints, and keeps all detail inline rather than splitting long reference material into separate files.

Suggestions

Add explicit validation/verification checkpoints to the emulation guidance (e.g. confirm payload detonates, verify C2 check-in, validate collected data before exfil) to raise workflow clarity above the cap.

Move the lengthy 'Notable campaigns' histories and 'Detection & defense' detail into separate reference files (e.g. CAMPAIGNS.md, DETECTION.md) linked from the overview to improve progressive disclosure and conciseness.

Trim the campaign narrative prose to the TTP-relevant facts so the body stays focused on emulation tradecraft.

DimensionReasoningScore

Conciseness

The body is information-dense and threat-actor-specific rather than explaining basics Claude knows, but the lengthy historical campaign narratives and broad detection section add padding that could be trimmed for an emulation-focused skill.

3 / 5

Actionability

The emulation guidance gives concrete, specific direction — named CVEs (CVE-2017-11882, CVE-2017-0199), a real PowerShell pattern, target file extensions, AES+base64 encoding, and named tools (QuasarRAT/Sliver) — with only minor gaps around how to actually obtain or build the exploits.

4 / 5

Workflow Clarity

TTPs are organized by ATT&CK tactic giving an implicit kill-chain sequence, but there are no explicit validation checkpoints or feedback loops, and the rubric caps destructive/batch-operation workflows at 3 when validation is missing.

3 / 5

Progressive Disclosure

Section headers provide reasonable structure, but at ~180 lines the campaign histories, full TTP catalog, and detection guidance are all inlined in one file with no one-level-deep reference files, despite no bundle files existing to offload them.

3 / 5

Total

13

/

20

Passed

Description

65%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 specific and highly distinctive, naming Patchwork and many aliases that match natural user triggers, but it omits any explicit 'Use when...' clause and lists only a single nominal action rather than concrete capabilities.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when emulating Patchwork/Dropping Elephant TTPs in an authorized engagement or mapping them to MITRE ATT&CK.'

Append concrete capabilities beyond 'profile', such as 'documents TTPs, signature malware, and emulation guidance for the Patchwork threat actor'.

Consider adding common trigger variants like 'APT' or 'India espionage emulation' alongside the existing aliases.

DimensionReasoningScore

Specificity

Names the domain ('Adversary-emulation profile') and a concrete subject (Patchwork with multiple aliases) but states only a single nominal action ('profile for...') rather than listing concrete capabilities, leaving coverage incomplete.

3 / 5

Completeness

The 'what' is clear (an adversary-emulation profile for a named actor) but there is no 'Use when...' or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Surfaces numerous natural actor aliases a user would say ('Patchwork', 'Dropping Elephant', 'Chinastrats', 'MONSOON', 'Hangover Group', 'Operation Hangover') plus 'G0040' and 'cyber-espionage', giving strong keyword coverage though a few common variants ('APT', 'India espionage') are absent.

4 / 5

Distinctiveness Conflict Risk

Targets a uniquely named threat actor with many aliases and a narrow niche (India-linked espionage emulation), making it highly distinguishable with minimal risk of triggering for an unrelated skill.

5 / 5

Total

15

/

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/shared/adversary-emulation/patchwork/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.