CtrlK
BlogDocsLog inGet started
Tessl Logo

cloud-attack-methods

云攻击:元数据API,S3/K8s,AWS/Azure/GCP身份提权,MinIO矩阵,阿里云FC,ChengZi SDK解密。Use when attacking cloud metadata, IAM, K8s, MinIO, Aliyun FC, or cloud post-ex.

60

Quality

71%

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 ./skills/cloud-attack-methods/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

55%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 body is a dense, concrete attack reference that is token-efficient and largely actionable, but it is a monolithic code block with no structured sequencing, validation checkpoints, or progressive disclosure into separate files. The destructive/offensive operations lack the feedback loops the rubric requires.

Suggestions

Add explicit validation/verification checkpoints to each destructive chain (e.g., confirm privesc succeeded, verify a stolen token is valid before reuse, check a CVE path returns the leak before pivoting) so workflows have feedback loops rather than flat technique lists.

Split the monolithic code block into a concise overview in SKILL.md plus separate reference files (e.g., references/minio.md, references/aliyun-fc.md, references/chengzi-sdk.md) with clearly signaled one-level-deep links.

Number the steps within each attack chain (identify → fingerprint → exploit → verify) instead of relying on emoji markers, so the sequence and checkpoints are explicit.

DimensionReasoningScore

Conciseness

The body is maximally lean with no concept re-explanation or padding, but the single dense jargon code block sacrifices readability; a structured version would be equally token-efficient and clearer.

4 / 5

Actionability

Many entries are concrete and copy-paste ready ('aws s3 ls --no-sign-request', the MinIO login POST body, CVE-2023-28432 path, XOR key=0x96), but several are endpoint or flag names only without full executable commands.

4 / 5

Workflow Clarity

A rough identify→exploit pattern is implicit in some sections, but there is no numbered sequence and no validation/verification checkpoints for destructive offensive operations, which caps this dimension at 3 and the content sits below it.

2 / 5

Progressive Disclosure

Everything is inlined into one monolithic code block under a single heading; the MinIO matrix, Aliyun FC, and ChengZi SDK sections clearly belong in separate reference files, and no bundle files exist.

2 / 5

Total

12

/

20

Passed

Description

87%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 strong, specific description that clearly states what the skill covers and when to invoke it, with a concrete trigger clause. Minor weakness is that the capability list leans on target names over explicit action verbs and omits a few natural provider/S3 keywords.

DimensionReasoningScore

Specificity

Lists several concrete targets and a couple of explicit actions ('AWS/Azure/GCP身份提权', 'ChengZi SDK解密', '元数据API', 'MinIO矩阵'), but most entries are domains/objects rather than verbs, leaving a minor gap versus comprehensive action coverage.

4 / 5

Completeness

Explicitly answers both 'what' (the comma-separated capability list) and 'when' (a concrete 'Use when attacking...' trigger clause) with concrete trigger phrases.

5 / 5

Trigger Term Quality

The 'Use when attacking cloud metadata, IAM, K8s, MinIO, Aliyun FC, or cloud post-ex' clause covers natural terms well, but omits provider names (AWS/Azure/GCP), S3, and 'privesc' that users would also say.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear cloud-attack niche with distinct triggers (metadata, IAM, K8s, MinIO, Aliyun FC, cloud post-ex) and minimal overlap risk with non-cloud skills.

5 / 5

Total

18

/

20

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
Ed1s0nZ/CyberStrikeAI
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.