Content
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable AWS penetration testing skill with concrete, executable commands covering a broad range of attack techniques. Its main weaknesses are the lack of validation checkpoints in multi-step destructive workflows (e.g., no verification after privilege escalation, no rollback guidance), and the monolithic structure that could benefit from splitting advanced topics into referenced files. The content is mostly efficient but has some redundancy and filler sections.
Suggestions
Add explicit validation/verification steps after destructive operations (e.g., 'Verify escalation: aws sts get-caller-identity' after each privilege escalation technique, rollback commands for cleanup)
Split the lengthy content into referenced sub-files (e.g., s3-exploitation.md, privilege-escalation.md, ec2-exploitation.md) and keep SKILL.md as a concise overview with navigation links
Remove the redundant 'When to Use' section and trim the Purpose section since it duplicates the description
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some unnecessary verbosity—the Purpose section repeats the description, the 'When to Use' section is a meaningless tautology, and some sections like the tool table include installation commands Claude could infer. However, most content is command-focused and reasonably efficient. | 2 / 3 |
Actionability | The skill provides fully executable bash commands and Python code throughout, with specific AWS CLI commands, concrete examples of SSRF exploitation, privilege escalation techniques with copy-paste ready code, and clear command-output expectations. Nearly every technique has a concrete, runnable example. | 3 / 3 |
Workflow Clarity | The core workflow has numbered steps (1-3) for initial enumeration, but the overall engagement flow lacks explicit validation checkpoints and feedback loops. For destructive operations like disabling CloudTrail or modifying Lambda code, there are no verification steps or rollback procedures. The Constraints section mentions documentation but doesn't integrate it into the workflow. | 2 / 3 |
Progressive Disclosure | The skill references an advanced file (references/advanced-aws-pentesting.md) for deeper topics, which is good one-level-deep disclosure. However, no bundle files are provided to support this reference, and the main file itself is quite long (~300+ lines) with sections like EC2 exploitation and SSM that could be split into separate reference files for better organization. | 2 / 3 |
Total | 9 / 12 Passed |