CC performing-aws-privilege-escalation-assessment
Performing authorized privilege escalation assessments in AWS environments to identify IAM misconfigurations that allow users or roles to elevate their permissions using Pacu, CloudFox, Principal Mapper, and manual IAM policy analysis techniques.
Performing authorized privilege escalation assessments in AWS environments to identify IAM misconfigurations that allow users or roles to elevate their…
As a process C 61/100 · Has gaps — weak spots: failures and branches, running it twice, progress reporting
How to improve
For the model run — optional
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 10
✓ No critical or high findings
Medium and low: 10
-
low Risky intent
intent-offensive-securityreferences/api-reference.md:1Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# API Reference: Performing AWS Privilege Escalation Assessment
-
low Risky intent
intent-offensive-securityreferences/api-reference.md:21Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| `sts.assume_role(RoleArn, RoleSessionName)` | Assume a role for privilege escalation test |
-
low Risky intent
intent-offensive-securityreferences/api-reference.md:28Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)| `iam__privesc_scan` | Scan for 21+ privilege escalation vectors |
detector -
low Risky intent
intent-offensive-securityreferences/api-reference.md:37Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **cloudfox**: Cloud penetration testing tool for AWS enumeration
-
low Risky intent
intent-offensive-securityreferences/api-reference.md:59Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- [Rhino Security: AWS IAM Privilege Escalation](https://rhinosecuritylabs.com/aws/aws-privilege-escalation-methods-mitigation/)
-
low Risky intent
intent-offensive-securitySKILL.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)description: 'Performing authorized privilege escalation assessments in AWS environments
quoted -
low Risky intent
intent-offensive-securitySKILL.md:33Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Performing AWS Privilege Escalation Assessment
-
low Risky intent
intent-offensive-securitySKILL.md:37Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- When conducting authorized penetration testing of AWS IAM configurations
-
low Risky intent
intent-offensive-securitySKILL.md:41Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- When evaluating cross-account trust relationships for privilege escalation risks
-
low Risky intent
intent-offensive-securitySKILL.md:43Offensive-security / dual-use content (legitimate for authorised testing; review intended use)**Do not use** for unauthorized testing against AWS accounts, for assessing non-IAM attack vectors (SSRF, application vulnerabilities), or as a substitute for comprehensive cloud penetration testing.
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "domain" - note
frontmatter-keyunknown frontmatter key "subdomain" - note
frontmatter-keyunknown frontmatter key "nist_csf" - note
frontmatter-keyunknown frontmatter key "mitre_attack"
Process rating: all ten parameters 61/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 6 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 22 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2933 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- -41 reference files, but SKILL.md never points to them: the model will not open them
- -31 of 1 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 246: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 22 items
- +3Output format is stated explicitly
- +4Has examples (7 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.