education-suite — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited education-suite (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 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.
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 education system analysis agent. Do NOT ask the user questions. Execute all four phases sequentially without pausing.
INPUT: $ARGUMENTS Pass the system name, specific areas to analyze, student population focus, or grade level scope (e.g., "high school SIS dropout prevention" or "district-wide curriculum review").
============================================================ PHASE 1: DROPOUT RISK ANALYSIS (/dropout-risk) ============================================================
Follow the instructions defined in the /dropout-risk skill exactly.
Analyze the student information system for dropout risk factors and early warning capabilities:
Capture all findings. The at-risk populations and risk factors identified here drive personalization priorities in Phase 3 and resource allocation analysis in Phase 4.
============================================================ PHASE 2: CURRICULUM OPTIMIZATION (/curriculum-optimizer) ============================================================
Follow the instructions defined in the /curriculum-optimizer skill exactly.
Analyze curriculum management for alignment, coverage, and quality:
CROSS-REFERENCE WITH PHASE 1: Identify whether curriculum design contributes to dropout risk. Courses with high failure rates may indicate curriculum issues rather than student deficiency. Flag subjects where at-risk populations disproportionately struggle.
============================================================ PHASE 3: STUDENT PERSONALIZATION (/student-personalization) ============================================================
Follow the instructions defined in the /student-personalization skill exactly.
Analyze adaptive learning and differentiated instruction capabilities:
CROSS-REFERENCE WITH PHASES 1 AND 2: At-risk students from Phase 1 should receive the most intensive personalization. Curriculum gaps from Phase 2 should inform where personalization fills the gaps. Flag misalignment between identified risk factors and available personalization strategies.
============================================================ PHASE 4: SCHOOL OPERATIONS REVIEW (/school-ops) ============================================================
Follow the instructions defined in the /school-ops skill exactly.
Analyze operational efficiency and resource allocation:
CROSS-REFERENCE WITH ALL PRIOR PHASES: Dropout prevention programs from Phase 1 need adequate counselor staffing. Curriculum improvements from Phase 2 need instructional time and materials budget. Personalization from Phase 3 depends on technology infrastructure and specialist staffing. Flag every operational constraint that limits the effectiveness of interventions identified earlier.
============================================================ 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 | /dropout-risk | PASS/FAIL | {N} risk factors, {N} early warning gaps, {N} intervention issues |
| 2 | /curriculum-optimizer | PASS/FAIL | {N} alignment issues, {N} coverage gaps, {N} pacing concerns |
| 3 | /student-personalization | PASS/FAIL | {N} personalization gaps, {N} accommodation issues |
| 4 | /school-ops | PASS/FAIL | {N} resource constraints, {N} efficiency opportunities |
Student outcome risk: {LOW / MEDIUM / HIGH} System maturity: {EMERGING / DEVELOPING / ESTABLISHED / OPTIMIZING}
[Issues that span multiple phases — these represent systemic gaps where student outcomes are affected by the interaction of curriculum, personalization, operations, and risk detection]
| Finding | Student Impact | Feasibility | Priority |
|---|---|---|---|
| [finding] | [high/med/low] | [high/med/low] | [1-N] |
Immediate (0-30 days):
Short-term (1-3 months):
Long-term (3-12 months):
NEXT STEPS:
/teacher-workload to assess educator capacity for recommended interventions/security-review to audit access controls on student data systemsDO 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:
### /education-suite — {{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.