Is deploy-it-ticket-resolution safe to install?

SaferSkills independently audited deploy-it-ticket-resolution (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

CategoryWeightCategory scoreContribution

Securityprompt, exec, net, exfil, eval

35%

100

35.0 pts

Supply chainhash, typosquat, maintainer, lockfile

20%

100

20.0 pts

Maintenancestaleness, pinning, CI

15%

100

15.0 pts

TransparencySKILL.md, perms, README

15%

100

15.0 pts

Communityinstalls, verify, response

15%

100

15.0 pts

Findings & checks · 0 flagged

Securityscore 100 · 0 findings

✓—All security checks passedNo findings in this category for the latest scan.pass

Supply chainscore 100 · 0 findings

✓—All supply chain checks passedNo findings in this category for the latest scan.pass

Maintenancescore 100 · 0 findings

✓—All maintenance checks passedNo findings in this category for the latest scan.pass

Transparencyscore 100 · 0 findings

✓—All transparency checks passedNo findings in this category for the latest scan.pass

Communityscore 100 · 0 findings

✓—All community checks passedNo findings in this category for the latest scan.pass

The primary manifest — the file an agent reads to learn what this artifact does.

solution-plays/05-it-ticket-resolution/.github/skills/deploy-it-ticket-resolution/SKILL.md · 1 file

solution-plays/05-it-ticket-resolution/.github/skills/deploy-it-ticket-resolution/SKILL.md4.1 KB · Markdown

name: deploy-it-ticket-resolution

description: "Deploy IT Ticket AI — configure classification pipeline, routing rules, knowledge base integration, SLA tracking, PII masking. Use when: deploy, provision, configure."

Deploy IT Ticket Resolution

When to Use

Deploy or provision the IT ticket classification and routing pipeline
Configure knowledge base integration for auto-resolution
Set up SLA tracking and escalation rules
Configure PII masking for ticket content
Integrate with ITSM platforms (ServiceNow, Jira)

Prerequisites

Azure CLI authenticated: az account show
Bicep CLI: az bicep version
ITSM platform access (ServiceNow/Jira API credentials)
Knowledge base content prepared (FAQ docs, runbooks)
Target resource group with Contributor access

Step 1: Validate Infrastructure

az bicep lint -f infra/main.bicep
az bicep build -f infra/main.bicep

Verify resources:

Azure OpenAI (gpt-4o-mini for classification, gpt-4o for resolution)
Azure AI Search (knowledge base indexing)
Azure Storage (ticket attachments, KB documents)
Azure Key Vault (ITSM API keys, connection strings)
Azure Monitor (SLA tracking, classification metrics)

Step 2: Deploy Azure Resources

az deployment group create \
  --resource-group $RESOURCE_GROUP \
  --template-file infra/main.bicep \
  --parameters infra/parameters.json

Step 3: Configure Classification Pipeline

Deploy classification model with category taxonomy
Categories: Hardware, Software, Network, Access, Account, Other
Priority levels: P1 (Critical), P2 (High), P3 (Medium), P4 (Low)
Confidence threshold: route to human if confidence < 0.85

Step 4: Set Up Knowledge Base

# Index KB documents into Azure AI Search
python scripts/index_knowledge_base.py --source docs/kb/ --index it-kb-index

Index runbooks, FAQ docs, troubleshooting guides
Configure semantic ranking for KB retrieval
Set up hybrid search (keyword + vector) for best recall

Step 5: Configure Routing Rules

Priority	SLA Target	Routing
P1 Critical	1 hour	Immediate human + AI assist
P2 High	4 hours	AI auto-resolve, escalate if failed
P3 Medium	8 hours	AI auto-resolve, queue for human review
P4 Low	24 hours	AI auto-resolve, auto-close if resolved

Step 6: Configure PII Masking

Enable PII detection on ticket body, comments, attachments
Mask: SSN, credit card, phone, email, employee ID
Log masked version only (never store raw PII in logs)

Step 7: ITSM Integration

# Test ServiceNow API connectivity
python scripts/test_itsm.py --platform servicenow --endpoint $SNOW_INSTANCE

Configure webhook for new ticket events
Set up bidirectional sync (AI resolution → ticket update)
Map AI categories to ITSM categories

Step 8: Smoke Test

python scripts/test_classification.py --ticket "My laptop screen is flickering"
python scripts/test_resolution.py --ticket "How do I reset my VPN password?"
python scripts/test_routing.py --ticket "Production server down" --expected-priority P1

Troubleshooting

Issue	Cause	Fix
Wrong classification	Ambiguous ticket text	Improve system prompt with examples
Low confidence on all tickets	Temperature too high	Set temperature=0.0 for classification
KB retrieval returns irrelevant docs	Missing semantic config	Enable semantic reranking
PII not detected	Locale mismatch	Set correct locale in Content Safety config
SLA breach not triggered	Timer not started	Verify webhook fires on ticket creation
ITSM sync fails	Auth token expired	Implement token refresh in integration
Duplicate tickets created	No dedup logic	Hash ticket content for dedup check
Escalation loop	No max-escalation limit	Set max 3 escalation attempts

CI/CD Integration

# Add to CI pipeline after deployment
- name: Validate Classification
  run: python evaluation/eval.py --metrics classification --ci-gate
- name: Validate PII Detection
  run: python evaluation/eval.py --metrics pii --ci-gate

deploy-it-ticket-resolution— agent skill

Is deploy-it-ticket-resolution safe to install?

Deploy IT Ticket Resolution

When to Use

Prerequisites

Step 1: Validate Infrastructure

Step 2: Deploy Azure Resources

Step 3: Configure Classification Pipeline

Step 4: Set Up Knowledge Base

Step 5: Configure Routing Rules

Step 6: Configure PII Masking

Step 7: ITSM Integration

Step 8: Smoke Test

Troubleshooting

CI/CD Integration

Audit the pieces. Scan the whole. Decide.