Install
$ agentstack add skill-aws-samples-sample-ai-agent-skills-auditmanager-troubleshooting ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
AWS Audit Manager Diagnostics
When to use
Any AWS Audit Manager investigation — assessment creation, framework selection, control evaluation, evidence collection, delegation management, report generation, or custom framework configuration.
Investigation workflow
Step 1 — Collect and triage
aws auditmanager get-settings --attribute ALL
aws auditmanager list-assessments --query 'assessmentMetadata[*].{Id:id,Name:name,Status:status}'
version: "1.0.0"
last_updated: "2025-04-12"
aws auditmanager list-assessment-frameworks --frameworkType Standard --query 'frameworkMetadataList[*].{Id:id,Name:name,Type:type}'
version: "1.0.0"
last_updated: "2025-04-12"
Step 2 — Domain deep dive
aws auditmanager get-assessment --assessment-id
aws auditmanager get-evidence-folder --assessment-id --control-set-id --evidence-folder-id
aws auditmanager list-assessment-control-insights-by-control-domain --control-domain-id
Step 3 — Detailed investigation
aws cloudtrail lookup-events --lookup-attributes AttributeKey=EventSource,AttributeValue=auditmanager.amazonaws.com --max-results 20
aws auditmanager get-assessment-report-url --assessment-id --assessment-report-id
aws config describe-config-rules --query 'ConfigRules[*].{Name:ConfigRuleName,State:ConfigRuleState}'
version: "1.0.0"
last_updated: "2025-04-12"
Read references/guardrails.md before concluding on any Audit Manager issue.
Tool quick reference
| Tool / API | When to use | |------------|-------------| | auditmanager list-assessments | List assessments | | auditmanager get-assessment | Get assessment details | | auditmanager list-assessment-frameworks | List frameworks | | auditmanager get-evidence-folder | Get evidence details | | auditmanager create-assessment | Create new assessment | | auditmanager get-settings | Check Audit Manager settings |
Gotchas: AWS Audit Manager
- Audit Manager requires AWS Config to be enabled for automated evidence collection. Without Config, many controls cannot collect evidence automatically.
- Evidence collection is NOT real-time. It follows a schedule based on the control type. Manual evidence must be uploaded separately.
- Frameworks are templates — they define which controls to evaluate. Standard frameworks (CIS, PCI DSS, SOC 2) cannot be modified. Create custom frameworks for modifications.
- Delegation assigns control sets to team members for review. Delegates need IAM permissions to access Audit Manager and the delegated assessment.
- Assessment reports are generated as PDF/CSV and stored in the configured S3 bucket. The S3 bucket must exist and have proper permissions.
- Audit Manager is regional. Assessments in one region don't include resources from other regions.
Anti-hallucination rules
- Always cite specific assessment IDs, control statuses, or API responses as evidence.
- AWS Config must be enabled for automated evidence. Never assume evidence collection works without Config.
- Standard frameworks cannot be modified. Never suggest editing built-in frameworks.
- Evidence collection is scheduled, not real-time. Never claim instant evidence.
- Spend no more than 2 minutes on any single hypothesis. Pivot if inconclusive.
14 runbooks
| Category | IDs | Covers | |----------|-----|--------| | A — Assessment | A1-A2 | Creation, configuration | | B — Frameworks | B1-B2 | Standard frameworks, custom frameworks | | C — Controls | C1-C2 | Control evaluation, control status | | D — Evidence | D1-D3 | Automated collection, manual evidence, evidence quality | | E — Delegation | E1-E2 | Delegation setup, delegate access | | F — Reports | F1-F2 | Report generation, report access | | Z — Catch-All | Z1 | General troubleshooting |
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: aws-samples
- Source: aws-samples/sample-ai-agent-skills
- License: MIT-0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.