fin7

FIN7 (Carbon Spider / Sangria Tempest) adversary-emulation playbook — revenue-targeted spearphishing with phone follow-up, EDR-evasion tradecraft, AD compromise, and big-game-hunting ransomware. Use when emulating a high-end financially-motivated crew that graduated from POS theft to ransomware. Triggers on: 'emulate FIN7', 'Carbanak', 'Carbon Spider', 'Sangria Tempest', 'big game hunting', 'EDR evasion', 'AvNeutralizer'.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

75%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, well-structured adversary-emulation playbook with concrete templates, explicit safety/authorization gates, and clear cross-skill navigation. It is lean and actionable, with only minor redundancy and reliance on referenced skills preventing top marks.

Suggestions

Collapse the 'CONOPS kill_chain' section or fold it into the kill-chain table to remove the phase restatement and tighten conciseness.

Add a per-phase validate/verify checkpoint (e.g., confirm beacon + EDR-tamper rollback before advancing) to elevate workflow clarity on this destructive skill.

Resolve or verify the referenced paths (../../references/apt-groups.md and /skills/standard/*) so the progressive-disclosure navigation points to real files.

Dimension	Reasoning	Score
Conciseness	Lean and well-organized with no concept over-explanation, but the 'CONOPS kill_chain' section restates the kill-chain table and the 'When to emulate' bullets partly restate the description — minor trimming possible.	4 / 5
Actionability	Provides copy-paste-ready JSON templates, specific MITRE TTPs, and concrete per-phase skill paths, but relies on referenced external skills and leaves '<fill>' placeholders, leaving minor gaps.	4 / 5
Workflow Clarity	A clearly sequenced 11-phase kill chain with explicit safety gates, an EMERGENCY abort string, deconfliction, and canary-only validation — the destructive-operation cap does not apply since validation is present, though per-phase validate-then-proceed loops are only implied.	4 / 5
Progressive Disclosure	Well-structured sections with clearly signaled one-level references (backtick paths to other skills), but no bundle files exist and the external referenced paths cannot be verified, leaving minor organization gaps.	4 / 5
	Total	16 / 20 Passed

Description

100%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.

An exemplary description: specific capabilities, comprehensive trigger terms with synonyms, explicit what-and-when guidance, and a distinct niche. Voice is imperative third-person ('Use when...'), matching the good reference examples with no voice penalty.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'revenue-targeted spearphishing with phone follow-up, EDR-evasion tradecraft, AD compromise, and big-game-hunting ransomware' — giving comprehensive coverage of the playbook's capabilities.	5 / 5
Completeness	Explicitly answers both what (adversary-emulation playbook with specific TTPs) and when ('Use when emulating a high-end financially-motivated crew that graduated from POS theft to ransomware'), plus a concrete 'Triggers on:' clause.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage with synonyms and aliases — 'emulate FIN7', 'Carbanak', 'Carbon Spider', 'Sangria Tempest', 'big game hunting', 'EDR evasion', 'AvNeutralizer' — terms a user would naturally say.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear, narrow niche (FIN7 adversary emulation) with highly specific actor aliases, making conflict with other skills minimal.	5 / 5
	Total	20 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: PurpleAILAB/Decepticon
Path: packages/decepticon/decepticon/skills/standard/soundwave/threat-profile/emulation/fin7/SKILL.md
Commit: 0cf691e

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.