aws-penetration-testing
This skill should be used when the user asks to "pentest AWS", "test AWS security", "enumerate IAM", "exploit cloud infrastructure", "AWS privilege escalation", "S3 bucket testing...
Install with Tessl CLI
npx tessl i github:boisenoise/skills-collections --skill aws-penetration-testing77
Quality
72%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/antigravity-aws-penetration-testing/SKILL.mdDiscovery
72%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description excels at trigger term coverage and distinctiveness, providing excellent keywords that security professionals would naturally use. However, it reads more like a list of trigger phrases than a proper skill description - it's missing a clear statement of what the skill actually does (the capabilities). The description appears truncated with '...' suggesting incomplete content.
Suggestions
Add a clear capability statement at the beginning describing what the skill does, e.g., 'Performs AWS security assessments, identifies IAM misconfigurations, tests S3 bucket permissions, and discovers privilege escalation paths.'
Restructure to follow the pattern: [What it does] + 'Use when...' [trigger conditions] rather than leading with trigger phrases only.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists some specific actions like 'enumerate IAM', 'exploit cloud infrastructure', 'AWS privilege escalation', 'S3 bucket testing' but these are more trigger phrases than concrete capability descriptions. Missing explicit statements of what the skill actually does (e.g., 'Performs security assessments', 'Identifies misconfigurations'). | 2 / 3 |
Completeness | The description focuses heavily on 'when' (trigger phrases) but lacks a clear 'what does this do' statement. It reads as a list of trigger conditions rather than a balanced description of capabilities plus usage triggers. The 'Use when...' equivalent is present but the capability explanation is missing. | 2 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'pentest AWS', 'test AWS security', 'enumerate IAM', 'exploit cloud infrastructure', 'AWS privilege escalation', 'S3 bucket testing'. These are realistic phrases security professionals would use. | 3 / 3 |
Distinctiveness Conflict Risk | Very clear niche focused specifically on AWS security testing/pentesting. The specific terms like 'IAM', 'S3 bucket', 'AWS privilege escalation' create a distinct domain unlikely to conflict with general security or other cloud provider skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive AWS penetration testing skill with strong actionability through executable commands and good organization. The main weaknesses are missing validation checkpoints for destructive operations (CloudTrail deletion, privilege escalation) and some verbosity that could be trimmed. The skill would benefit from explicit verification steps after each exploitation technique.
Suggestions
Add explicit validation steps after privilege escalation attempts (e.g., 'Verify: aws sts get-caller-identity to confirm new permissions')
Include feedback loops for destructive operations like CloudTrail modification (e.g., 'Verify trail status before/after: aws cloudtrail describe-trails')
Remove explanatory sentences that Claude already knows (e.g., 'Systems Manager allows command execution on EC2 instances') to improve conciseness
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good use of tables and code blocks, but includes some unnecessary explanations (e.g., 'Systems Manager allows command execution on EC2 instances') and could be tightened in places. The tool table descriptions are somewhat redundant. | 2 / 3 |
Actionability | Provides fully executable commands and code throughout. Commands are copy-paste ready with clear syntax, including specific AWS CLI commands, Python code for Lambda exploitation, and curl commands for metadata access. | 3 / 3 |
Workflow Clarity | Steps are listed and sequenced (Step 1-3), but lacks explicit validation checkpoints for risky operations. The 'Covering Tracks' section describes destructive actions without verification steps, and privilege escalation techniques lack feedback loops to confirm success. | 2 / 3 |
Progressive Disclosure | Well-organized with clear sections, quick reference table, and appropriate reference to advanced content in a separate file. The structure allows easy navigation from overview to specific techniques without deep nesting. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- 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.