Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Conduct systematic reviews of privileged accounts to validate access rights, identify excessive permissions, and enforce least privilege across PAM infrastructure.
.claude/skills/performing-privileged-account-access-review/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-19 | ✗→✓ | ▲ Improved | — | — |
| case-10 | ✗→✓ | ▲ Improved | — | — |
| case-16 | ✗→✓ | ▲ Improved | — | — |
| case-05 | ✗→✓ | ▲ Improved | — | — |
| case-17 | ✗→✓ | ▲ Improved | — | — |
Privileged Account Access Review is a critical identity governance process that validates whether users with elevated permissions still require their access. This review covers domain admins, service accounts, database administrators, cloud IAM roles, and application-level privileged accounts. Regular access reviews are mandated by SOC 2, PCI DSS, HIPAA, and SOX compliance frameworks, typically required quarterly for high-privilege accounts.
| Category | Examples | Risk Level | Review Frequency | |----------|----------|------------|-----------------| | Domain Admins | Enterprise Admin, Domain Admin, Schema Admin | Critical | Monthly | | Service Accounts | SQL service, backup agents, monitoring agents | High | Quarterly | | Cloud IAM | AWS root, Azure Global Admin, GCP Owner | Critical | Monthly | | Database Admin | DBA accounts, sa/sys accounts | High | Quarterly | | Application Admin | App admin roles, API keys with admin scope | Medium | Semi-annually | | Emergency/Break-glass | Firecall accounts, emergency access | Critical | After each use |
DISCOVER VALIDATE REMEDIATE MONITOR
│ │ │ │
├─ Enumerate all ├─ Verify business ├─ Remove excess ├─ Continuous
│ privileged accounts │ justification │ privileges │ monitoring
│ │ │ │
├─ Identify orphaned ├─ Confirm account ├─ Disable orphaned ├─ Anomaly
│ accounts │ ownership │ accounts │ detection
│ │ │ │
├─ Map permissions to ├─ Check compliance ├─ Enforce password ├─ Session
│ business roles │ with policies │ rotation │ recording
│ │ │ │
└─ Classify by risk └─ Review last usage └─ Implement JIT └─ Audit
level and activity access loggingEnumerate all privileged accounts across the environment:
Active Directory:
Cloud Platforms:
iam:* permissionsDatabases:
Each privileged account must be evaluated against:
For each account, the designated reviewer must:
Decision matrix:
| Condition | Action | |-----------|--------| | Active user, justified privilege | Certify - maintain access | | Active user, excessive privilege | Remediate - reduce to least privilege | | Inactive > 90 days | Disable account, notify owner | | No owner identified | Disable account, escalate to security | | SoD conflict detected | Remediate - reassign or add compensating controls | | Break-glass account | Verify last use was authorized, reset credentials |
After reviews are completed:
Generate review reports including:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +23 percentage points is the difference between those two pass rates over the 22 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.