CC exploiting-aws-with-pacu
Runs the Pacu AWS exploitation framework end-to-end — session and credential setup, IAM enumeration, automated privilege-escalation scanning via iam__privesc_scan, and persistence/backdooring modules like iam__backdoor_users_keys. Use for authorized AWS penetration tests or red-team engagements, assessing blast radius from a compromised IAM credential, or generating attacker telemetry for purple-team detection testing.
Runs the Pacu AWS exploitation framework end-to-end — session and credential setup, IAM enumeration, automated privilege-escalation scanning via…
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches
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:37Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)| `iam__privesc_scan` | Privesc | Detect/exploit privilege-escalation paths |
detector -
low Risky intent
intent-offensive-securityreferences/api-reference.md:46Offensive-security / dual-use content (legitimate for authorised testing; review intended use)## Common privesc primitives checked by `iam__privesc_scan`
-
low Risky intent
intent-offensive-securityreferences/standards.md:7Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| PR.AA-05 | Access permissions, entitlements, and authorizations are defined, managed, enforced, and reviewed | Pacu privesc scanning demonstrates where IAM entitlements are over-permissive and explo
-
low Risky intent
intent-offensive-securityreferences/standards.md:15Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| T1098.003 | Account Manipulation: Additional Cloud Roles | Role-trust backdoors and privesc via policy modification. |
-
low Risky intent
intent-offensive-securityreferences/standards.md:23Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- AWS IAM Privilege Escalation methods — https://rhinosecuritylabs.com/aws/aws-privilege-escalation-methods-mitigation/
-
low Risky intent
intent-offensive-securitySKILL.md:15Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- cloud-pentest
-
low Risky intent
intent-offensive-securitySKILL.md:31Offensive-security / dual-use content (legitimate for authorised testing; review intended use)> **Legal Notice:** This skill is for authorized penetration testing and educational purposes only. Pacu performs active enumeration, privilege escalation, persistence, and backdooring against live AW
-
low Risky intent
intent-offensive-securitySKILL.md:35Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)Pacu is the open-source AWS exploitation framework from Rhino Security Labs. It is the cloud-pentest analogue of Metasploit: a modular Python console that manages target sessions, enumerates an AWS ac
detector -
low Risky intent
intent-offensive-securitySKILL.md:43Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Conducting an authorized AWS cloud penetration test or red-team engagement
-
low Risky intent
intent-offensive-securitySKILL.md:44Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Assessing the blast radius of a single compromised IAM credential (privesc scanning)
Files scanned: 5. 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 51/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 17 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 31 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2419 tokens
- low 11 top-level sections: this looks like several domains in one skill
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -42 reference files, but SKILL.md never points to them: the model will not open them
- +2Single-language instructions
- +3Description length 422: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 31 items
- +4Has examples (11 code blocks)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.