Menu
Scan cloud accounts and GitHub repos to discover AI/ML services and build an AI system inventory.
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
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.
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.
Launch the Shasta web dashboard to view compliance posture, findings, controls, and risk register in a browser.
| name | discover-ai |
| description | Scan cloud accounts and GitHub repos to discover AI/ML services and build an AI system inventory. |
| user-invocable | true |
You are helping a founder discover what AI/ML services are running in their cloud accounts and code repositories.
Read shasta.config.json for python_cmd, aws_profile, azure_subscription_id, and github_repos. Use that for all commands (shown as <PYTHON_CMD>).
For AWS (if aws_profile is set):
<PYTHON_CMD> -c "
import json
from shasta.config import get_aws_client
from shasta.aws.ai_discovery import discover_aws_ai_services
client = get_aws_client()
client.validate_credentials()
result = discover_aws_ai_services(client)
print(json.dumps(result, indent=2, default=str))
"
For Azure (if azure_subscription_id is set):
<PYTHON_CMD> -c "
import json
from shasta.config import get_azure_client
from shasta.azure.ai_discovery import discover_azure_ai_services
client = get_azure_client()
client.validate_credentials()
result = discover_azure_ai_services(client)
print(json.dumps(result, indent=2, default=str))
"
Whitney is the standalone source-code scanner, shipped at
github.com/transilienceai/whitney.
Install with pip install whitney if it is not already present.
whitney scan . --json > /tmp/whitney-findings.json 2>/dev/null || echo '[]' > /tmp/whitney-findings.json
<PYTHON_CMD> -c "
import json
data = json.load(open('/tmp/whitney-findings.json'))
for f in data:
sev = (f.get('severity') or 'info').upper()
print(f'[{sev}] {f.get(\"check_id\")}: {f.get(\"title\")}')
print(f'\nTotal: {len(data)} finding(s)')
"
Show a clear AI system inventory:
/ai-scan for full compliance assessment