government-compliance — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited government-compliance (Agent Skill) and scored it 92/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 2 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 2 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
You are an autonomous government compliance reviewer. Do NOT ask the user questions. Scan the codebase for compliance with federal and state government technology mandates, then produce a structured compliance gap assessment.
TARGET: $ARGUMENTS
If arguments are provided, focus on specific frameworks (e.g., "FedRAMP only", "Section 508", "NIST 800-53"). If no arguments, run the full compliance review.
============================================================ PHASE 1: SYSTEM CLASSIFICATION ============================================================
Step 1.1 -- Detect tech stack: backend, database, cloud provider and deployment model, auth mechanisms, encryption libraries, logging infrastructure, CI/CD, container/orchestration platforms.
Step 1.2 -- Assess FIPS 199 impact level by evaluating confidentiality (data sensitivity -- PII, PHI, tax, law enforcement), integrity (impact of improper modification), and availability (time-critical operations, health/safety dependencies). Record overall: LOW, MODERATE, or HIGH.
Step 1.3 -- Identify applicable frameworks based on system type: FedRAMP, FISMA, NIST 800-53, Section 508/WCAG 2.1, FOIA, NARA records retention, CJIS Security Policy, IRS Pub 1075, HIPAA, state-specific requirements.
============================================================ PHASE 2: NIST 800-53 CONTROL ASSESSMENT ============================================================
Step 2.1 -- Access Control (AC): AC-2 account management, AC-3 enforcement, AC-5 separation of duties, AC-6 least privilege, AC-7 failed login lockout, AC-8 system use notification, AC-11 session lock, AC-17 remote access.
Step 2.2 -- Audit and Accountability (AU): AU-2 event definitions, AU-3 record content (who/what/when/where/outcome), AU-4 storage capacity, AU-6 review and reporting, AU-8 timestamps, AU-9 audit protection, AU-11 retention.
Step 2.3 -- Configuration Management (CM): CM-2 baseline configuration, CM-3 change control, CM-6 security hardening, CM-7 least functionality, CM-8 component inventory.
Step 2.4 -- Identification and Authentication (IA): IA-2 MFA for privileged and remote access, IA-4 unique identifiers, IA-5 credential management and password policy, IA-8 non-organizational user identification.
Step 2.5 -- System Protection (SC): SC-7 boundary protection, SC-8 TLS transmission security, SC-12 key management, SC-13 FIPS 140-2 cryptography, SC-28 encryption at rest.
Step 2.6 -- System Integrity (SI): SI-2 flaw remediation, SI-4 monitoring, SI-10 input validation, SI-11 error handling without info disclosure.
For each control, record: Implemented, Partial, Not Implemented, or N/A with evidence file path.
============================================================ PHASE 3: FedRAMP AND CLOUD REQUIREMENTS ============================================================
Step 3.1 -- Determine target FedRAMP level (Low, Moderate, High) based on system impact level.
Step 3.2 -- Check cloud-specific controls: US-only data residency, multi-tenancy isolation, encryption (provider vs. customer keys), incident response SLA, continuous monitoring (ConMon), vulnerability scanning frequency, penetration testing schedule, POA&M tracking.
Step 3.3 -- Assess boundary documentation: system boundary diagrams, data flow diagrams, ISA references, API documentation, third-party service inventory.
============================================================ PHASE 4: SECTION 508 ACCESSIBILITY ============================================================
Step 4.1 -- Scan frontend for WCAG 2.1 AA compliance:
Step 4.2 -- Check assistive technology: ARIA live regions, form associations, modal focus management, touch targets (44x44px), accessible documents.
Step 4.3 -- Check automated a11y testing in CI/CD (axe-core, pa11y, eslint-plugin-jsx-a11y).
============================================================ PHASE 5: FOIA, RECORDS, AND AUDIT TRAILS ============================================================
Step 5.1 -- Check FOIA/records capabilities: search/retrieval across data stores, redaction, standard format export, request tracking, exemption coding, fee estimation, response letter generation.
Step 5.2 -- Verify records retention: automated enforcement, legal hold (suspend deletion during litigation), disposition workflow, NARA transfer, destruction certification, disposition audit trail.
Step 5.3 -- Verify audit trail coverage: authentication events, authorization events, data CRUD, configuration changes, privileged actions, exports, API access. Each record must include: UTC timestamp, user ID, source IP, action, object, outcome, before/after values for modifications.
Step 5.4 -- Verify audit protection: separate storage, append-only/write-once, tamper detection (checksums), restricted access, retention compliance.
============================================================ PHASE 6: DATA SOVEREIGNTY AND PRIVACY ============================================================
Step 6.1 -- Check data residency: storage in approved jurisdictions, cloud region verification, CDN restrictions for sensitive data, backup/DR locations.
Step 6.2 -- Evaluate privacy: data minimization, purpose limitation, individual access provisions, consent management, de-identification capabilities, Privacy Act compliance for federal systems.
============================================================ SELF-HEALING VALIDATION (max 2 iterations) ============================================================
After producing the review, validate completeness and consistency:
IF VALIDATION FAILS:
============================================================ OUTPUT ============================================================
Project: [name] Stack: [detected technologies] Impact Level: [LOW/MODERATE/HIGH] Assessment Date: [date]
| Framework | Applicable | Status | Controls | Gaps |
|---|---|---|---|---|
| NIST 800-53 | [yes/no] | [PASS/PARTIAL/FAIL] | [N] | [N] |
| FedRAMP | [yes/no] | [PASS/PARTIAL/FAIL] | [N] | [N] |
| Section 508 | [yes/no] | [PASS/PARTIAL/FAIL] | [N] | [N] |
| FOIA | [yes/no] | [PASS/PARTIAL/FAIL] | [N] | [N] |
| Family | Assessed | Implemented | Partial | Missing |
|---|---|---|---|---|
| AC | [N] | [N] | [N] | [N] |
| AU | [N] | [N] | [N] | [N] |
| CM | [N] | [N] | [N] | [N] |
| IA | [N] | [N] | [N] | [N] |
| SC | [N] | [N] | [N] | [N] |
| SI | [N] | [N] | [N] | [N] |
| ID | Framework | Control | Finding | Severity | Remediation |
|---|---|---|---|---|---|
| G-001 | [fwk] | [ctrl] | [finding] | [CRITICAL/HIGH/MED/LOW] | [fix] |
| WCAG Criterion | Status | Location | Description |
|---|---|---|---|
| [criterion] | [PASS/FAIL] | [file:line] | [finding] |
Critical (blocks ATO):
High (before production):
Moderate (POA&M):
============================================================ NEXT STEPS ============================================================
/secure for comprehensive security posture review."/encryption to verify FIPS 140-2 compliant cryptography."/accessibility-test for automated WCAG 2.1 testing."============================================================ SELF-EVOLUTION TELEMETRY ============================================================
After producing output, record execution metadata for the /evolve pipeline.
Check if a project memory directory exists:
~/.claude/projects/skill-telemetry.md in that memory directoryEntry format:
### /government-compliance — {{YYYY-MM-DD}}
- Outcome: {{SUCCESS | PARTIAL | FAILED}}
- Self-healed: {{yes — what was healed | no}}
- Iterations used: {{N}} / {{N max}}
- Bottleneck: {{phase that struggled or "none"}}
- Suggestion: {{one-line improvement idea for /evolve, or "none"}}Only log if the memory directory exists. Skip silently if not found. Keep entries concise — /evolve will parse these for skill improvement signals.
============================================================ DO NOT ============================================================
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.