SKILLEMALL.ai
GitHub ↗ RU Sign in

AB dyagil-supabase-security-audit

Audit a Supabase + Vercel project for RLS coverage, privilege escalation, cross-customer data leaks, anonymous exposure, magic-link flow correctness, and HTTP security headers — and apply hotfix templates when issues are found. Use whenever the user asks about security / RLS / audits, after any migration that touches `profiles`-like tables or auth, or before exposing a new customer-facing surface.

ClawHub Agent Skills author: dyagil v1.0.0 MIT-0 5 files body ≈ 987 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process B 65/100 · Nearly there — weak spots: result and completion, running it twice

AnalyzerSupabaseInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
94/100
safety, quality, tests
Safety 60%
95
Quality 40%
92
Run on models
none yet
Process rating
B
65/100
Nearly there
Result and completion w 14
0
Running it twice w 4
30
Failures and branches w 10
55
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 5

    ✓ No critical or high findings

    Medium and low: 5
    • low Risky intent intent-offensive-security skill-card.md:2
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      Audits Supabase and Vercel projects for RLS coverage, privilege escalation, cross-customer data leaks, anonymous exposure, magic-link flow correctness, and HTTP security headers, then points agents to
    • low Risky intent intent-offensive-security SKILL.md:3
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      description: Audit a Supabase + Vercel project for RLS coverage, privilege escalation, cross-customer data leaks, anonymous exposure, magic-link flow correctness, and HTTP security headers — and apply
    • low Risky intent intent-offensive-security SKILL.md:58
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      Output is grouped: RLS coverage → anonymous exposure → UPDATE policies → live privilege escalation → cross-customer leaks → HTTP headers → summary.
    • low Risky intent intent-offensive-security SKILL.md:70
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
      The most common critical finding is **"UPDATE policy lacks WITH CHECK on role/email — privilege escalation risk"**. That has a turn-key SQL template:
      quoted
    • low Risky intent intent-offensive-security SKILL.md:88
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - **Penetration testing of business logic** (e.g. "can a customer call `/api/send-portal-link` for another customer's id?"). Spot-check those manually by tracing each `api/*.js` endpoint's auth check.

    Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 65/100

    • 0Result and completion. Does not say what the result is
    • 30Running it twice. 3 mutating operations with no state check
    • 55Failures and branches. 1 branches
    • 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 17 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 987 tokens
    • 100Progress reporting. Reports progress

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • +2Single-language instructions
    • +3Description length 400: enough signal without eating the budget
    • +4Structure: 10 headings
    • +3Step-by-step instructions: 17 items
    • +4Has examples (4 code blocks)
    • +4Reference files are cited in the instructions (1 of 1)
    • +3All 1 scripts are documented
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.

    External checks

    ClawHub: suspicious
    This Supabase audit skill appears purpose-built, but it needs review because it uses powerful database credentials and live database probes with broad triggering and unsafe defaults.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026