Menu
Connect to an AWS account, validate credentials, and discover what services are in use.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | connect-aws |
| description | Connect to an AWS account, validate credentials, and discover what services are in use. |
| user-invocable | true |
You are helping a semi-technical founder connect Shasta to their AWS account for SOC 2 compliance scanning.
Shasta uses shasta.config.json in the project root for all settings. Before running any commands, check if this file has aws_profile set. If not, you'll need to configure it.
Check if shasta.config.json is configured. Read the file. If aws_profile is empty, ask the user:
aws configure list-profiles to show options)Update shasta.config.json with their answers.
Also detect the correct Python command. Run python3 --version and python --version to find which works. Update python_cmd in the config.
Validate AWS credentials by running (substitute the correct python command and profile):
<PYTHON_CMD> -c "
from shasta.config import get_aws_client
c = get_aws_client()
info = c.validate_credentials()
services = c.discover_services()
print(f'AWS Account: {info.account_id}')
print(f'Aliases: {info.account_aliases or [\"none\"]}')
print(f'Identity: {info.user_arn}')
print(f'Region: {info.region}')
print(f'Services detected: {services if services else \"none (empty account)\"}')
"
Initialize the Shasta database:
<PYTHON_CMD> -c "from shasta.db.schema import ShastaDB; db = ShastaDB(); db.initialize(); print('Database initialized at data/shasta.db')"
Present results in a clear, friendly format and suggest running /scan next.
<PYTHON_CMD> with whatever works on this machine (python3, python, or py -3.12).aws configure --profile <name> or aws sso login.infra/shasta-scanning-policy.json (42 read-only permissions).Deep code scan for AI security issues — prompt injection, PII in prompts, hardcoded keys, unguarded agents.
Run AI governance checks across cloud accounts and code repos — ISO 42001, EU AI Act, NIST AI RMF compliance.
Scan cloud accounts and GitHub repos to discover AI/ML services and build an AI system inventory.
Walk staged changes against the engineering principles checklist and report pass/fail per principle. Run before any non-trivial commit. Catches doc drift, stub functions, single-region defaults, missing framework mappings, and other regressions before they ship.
Generate a public-facing security trust page from scan data. Produces a single deployable index.html that shows compliance framework scores, security policies, infrastructure overview, and data protection posture. Deployable to S3, Vercel, Netlify, or GitHub Pages.
Paste a vendor's domain. Get a security risk assessment in 60 seconds.