Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/cognisn/cloudledger/attack-path-analysisnpx skills add Cognisn/cloudledger --skill attack-path-analysisgit clone --depth 1 https://github.com/Cognisn/cloudledgerWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00088 | $0.01192 |
| Opus 5 | $0.00044 | $0.00596 |
| Sonnet 5 | $0.00018 | $0.00238 |
| Haiku 4.5 | $0.00009 | $0.00119 |
Grade A, and why
attack-path-analysis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Attack path analysis (MITRE ATT&CK)
Explain how an adversary could realistically compromise a scanned AWS account, as chained attack paths mapped to MITRE ATT&CK tactics and techniques — not an unordered list of findings.
The value is the chain: an internet-reachable instance is only the entry point; the risk is what it leads to (a permissive role, an unencrypted database, a public bucket). Build paths from entry to impact.
Tools
Gather the raw material, then correlate it:
analyze_service_exposure— the internet-reachable surface (EC2, Lambda, databases, entry points) with evidence chains. The entry points.get_security_assessment_data— the full findings set across identity, network, data, logging, service exposure. The weaknesses to chain.analyze_iam_permissions— over-privileged users/roles, admin/wildcard grants, missing MFA, stale keys. Returns{summary, findings}. The escalation and lateral-movement fuel.find_public_ec2_instances,find_publicly_accessible_databases,find_public_s3_buckets— specific exposed resources for concrete paths.find_security_group_violations— the network reachability that connects steps.get_iam_users— MFA and credential state for initial-access realism.
Workflow
1. Resolve the scan
Latest scan unless the user names one (list_scans accepts account_number).
State the account and scan date.
2. Enumerate the ingredients by tactic
Load references/attack-technique-map.md. Sort the findings into ATT&CK
tactics using it:
- Initial Access — internet-reachable instances/functions/databases, public entry points, users without MFA.
- Privilege Escalation / Credential Access — instance roles and users with broad or wildcard IAM, stale access keys, root weaknesses, unsecured credentials.
- Lateral Movement — permissive internal security groups, network connectivity, shared roles.
- Collection / Exfiltration / Impact — public or unencrypted data stores, public buckets, missing logging that would hide the activity.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 103 lines · 0 tokens per session scan A c70bb36a4d24
attack-path-analysis is a skill published in the GitHub repository Cognisn/cloudledger (0 stars, last pushed 13d ago), licensed MIT. It adds 88 tokens to every session and 1,192 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
aws-cloud-penetration-testing
Penetration test AWS cloud environments for misconfigurations, privilege escalation, data exposure, and lateral movement. Use this skill when assessing AWS accounts for security weaknesses including S3 bucket misconfigurations, IAM policy flaws, EC2 metadata exploitation, Lambda function abuse, and cross-account…
auditing-aws-s3-bucket-permissions
Systematically audit AWS S3 bucket permissions to identify publicly accessible buckets, overly permissive ACLs, misconfigured bucket policies, and missing encryption settings using AWS CLI, S3audit, and Prowler to enforce least-privilege data access controls.
asn-infrastructure-mapping
Map organization IP infrastructure via ASN, CIDR, TLD expansion, and reverse DNS.
detecting-aws-cloudtrail-anomalies
Detect unusual API call patterns in AWS CloudTrail logs using boto3, statistical baselining, and behavioral analysis to identify credential compromise, privilege escalation, and unauthorized resource access.
cloud-iam-deep
GCP/AWS/Azure cloud exploitation -- Cloud Functions, Firestore, Cloud Run, S3, MinIO, Blob Storage, SA keys.
port-mass-scan
Port scan /8-/24 with Masscan+RustScan and nmap banners.