housing-audit — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited housing-audit (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 affordable housing audit agent. Do NOT ask the user questions. Execute all four phases sequentially without pausing.
INPUT: $ARGUMENTS Pass the system name, property portfolio scope, or compliance focus (e.g., "Section 8 voucher program" or "LIHTC portfolio compliance review").
============================================================ PHASE 1: AFFORDABLE HOUSING MANAGEMENT (/affordable-housing) ============================================================
Follow the instructions defined in the /affordable-housing skill exactly.
Analyze the housing management system:
Record all findings. Housing inventory quality and tenant data accuracy directly affect eviction risk prediction in Phase 2 and rent burden analysis in Phase 4.
============================================================ PHASE 2: EVICTION RISK ANALYSIS (/eviction-risk) ============================================================
Follow the instructions defined in the /eviction-risk skill exactly.
Analyze eviction prevention capabilities:
CROSS-REFERENCE WITH PHASE 1: Affordable housing residents face elevated eviction risk due to income constraints. Identify data gaps where the housing management system fails to provide data the risk model needs. Flag properties with both high vacancy rates and high eviction rates — this indicates systemic operational issues.
============================================================ PHASE 3: HOUSING COMPLIANCE REVIEW (/housing-compliance) ============================================================
Follow the instructions defined in the /housing-compliance skill exactly.
Review against housing regulatory requirements:
CROSS-REFERENCE WITH PHASES 1 AND 2: A waitlist that violates Fair Housing preferences is both an operational and compliance failure. An eviction process that skips VAWA protections is both a risk management and compliance failure. Document these intersections explicitly with references to the specific Phase 1/2 findings.
============================================================ PHASE 4: RENT BURDEN ANALYSIS (/rent-burden) ============================================================
Follow the instructions defined in the /rent-burden skill exactly.
Analyze rent affordability and subsidy accuracy:
CROSS-REFERENCE WITH ALL PRIOR PHASES: Phase 1 housing data establishes the rent structure. Phase 2 eviction risk often stems directly from rent burden. Phase 3 compliance requires mathematically accurate rent calculations. Flag properties or populations where high rent burden, high eviction risk, and compliance gaps converge — these are the highest-priority intervention targets.
============================================================ SELF-HEALING VALIDATION (max 3 iterations) ============================================================
After completing all phases, validate the combined output:
STOP when:
IF STILL FAILING after 3 iterations:
============================================================ OUTPUT ============================================================
| Phase | Skill | Status | Findings |
|---|---|---|---|
| 1 | /affordable-housing | PASS/FAIL | {N} management issues, {N} waitlist concerns, {N} inventory gaps |
| 2 | /eviction-risk | PASS/FAIL | {N} risk model issues, {N} intervention gaps, {N} legal process concerns |
| 3 | /housing-compliance | PASS/FAIL | {N} compliance gaps ({N} Fair Housing, {N} HUD, {N} LIHTC) |
| 4 | /rent-burden | PASS/FAIL | {N} affordability issues, {N} subsidy calculation concerns |
Compliance verdict: {COMPLIANT / GAPS IDENTIFIED / NON-COMPLIANT} Tenant protection risk: {LOW / MEDIUM / HIGH} Affordability risk: {LOW / MEDIUM / HIGH}
[Issues spanning multiple phases -- high rent burden driving eviction risk, compliance gaps in eviction process, management data quality affecting risk prediction]
| Property/Program | Eviction Risk | Compliance Risk | Affordability Risk | Priority |
|---|---|---|---|---|
| [property] | [H/M/L] | [H/M/L] | [H/M/L] | [1-N] |
NEXT STEPS:
/security-review to audit access controls on tenant PII and financial data/government-compliance to expand compliance review beyond housing-specific regulationsDO NOT:
============================================================ 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:
### /housing-audit — {{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.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.