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/security-groups-reviewnpx skills add Cognisn/cloudledger --skill security-groups-reviewgit clone --depth 1 https://github.com/Cognisn/cloudledgerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cognisn/cloudledger/security-groups-review)<a href="https://agentmods.dev/skills/cognisn/cloudledger/security-groups-review"><img src="https://agentmods.dev/badge/skills/cognisn/cloudledger/security-groups-review.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.01079 |
| Opus 5 | $0.00044 | $0.00540 |
| Sonnet 5 | $0.00018 | $0.00216 |
| Haiku 4.5 | $0.00009 | $0.00108 |
Grade A, and why
security-groups-review 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 3d ago.
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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security groups review
Audit every security group in a scanned account and explain what each one actually exposes — not just list rules, but say what they mean for risk.
Tools
find_security_group_rules— every security group and its ingress/egress rules. Returns{security_groups, count}. This is the full inventory.find_security_group_violations— groups with overly permissive rules on sensitive ports, pre-analysed. Returns{summary, violations_by_port, security_groups_with_violations, recommendations}.analyze_service_exposure(serviceec2) — which instances are actually reachable through their attached groups, with the evidence chain.get_network_interfaces_with_public_ips— the ENIs that are internet-facing, to see which groups sit on a public edge. Returns{network_interfaces, count}.get_vpc_architecture/get_vpc_topology_detailed— where a group sits in the VPC, when the user wants topology context.search_by_ip— trace a specific CIDR or address through the groups.
Workflow
1. Resolve the scan and get the full inventory
Use the latest scan unless the user names a scan_id or account (list_scans
accepts an account_number filter). Call find_security_group_rules for the
complete set of groups and their rules, and report the total count — this review
covers all of them, not a sample.
2. Surface the violations first
Call find_security_group_violations. Lead the review with these: groups open
to 0.0.0.0/0 or ::/0 on sensitive ports (SSH 22, RDP 3389, databases
3306/5432/1433/27017/6379, and all-traffic rules). Use violations_by_port to
show what is exposed where, and carry the tool's recommendations into your own.
3. Turn rules into implications — the point of the review
For each notable group, do not just restate the rule; explain the consequence:
- World-open sensitive port → a directly reachable attack surface. Name the service on the port and the likely attacker action (e.g. SSH brute force, an unauthenticated database connection).
- All-traffic (
-1) from0.0.0.0/0→ every service behind the group is exposed; treat as high severity regardless of what is attached today. - Default security group with rules → applies to anything launched without an explicit group; unintended exposure.
- Broad internal CIDRs (e.g. 10.0.0.0/8) → lateral-movement surface; lower priority than world-open but note it for defence in depth.
- Egress wide open → note it as an exfiltration/uncontrolled-outbound path, distinct from ingress exposure.
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.
- 3d ago First seen · 87 lines · 0 tokens per session scan A 2fc1de023589
security-groups-review is a skill published in the GitHub repository Cognisn/cloudledger (0 stars, last pushed 15d ago), licensed MIT. It adds 88 tokens to every session and 1,079 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
cloud-iam-deep
GCP/AWS/Azure cloud exploitation -- Cloud Functions, Firestore, Cloud Run, S3, MinIO, Blob Storage, SA keys.
aws-essentials
Use when standing up the core AWS surface a small product needs: hardening a fresh account, a private S3 bucket, encrypted RDS Postgres, ECS Fargate vs EC2, CloudFront + OAC, or scoping an IAM policy to least privilege. NOT the CI pipeline that ships the container (that is deployment), NOT app-code access-control…
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…
aws-cdk-discipline
AWS infrastructure policy for fermi-agentcore - all changes through CDK committed to main, Fermi AWS access is read-only verification.
aws-expert
Expert-level AWS cloud architecture, services, security, cost optimization, and best practices.
alchemy-infra
Sets up Alchemy (alchemy-run/alchemy, Infrastructure-as-TypeScript) in any codebase — new project scaffold OR add to existing app. Wires Cloudflare/AWS providers, state backend, secrets, and binding types end-to-end with strict secret hygiene. USE THIS SKILL whenever the user mentions "alchemy", "alchemy.run"…