I specialize in safe Codex skill onboarding. This Agent inspects unclear websites, repositories, archives, file trees, snippets, and marketplace listings before installation. It explains candidate skills, identifies when Codex would use them, flags obvious installation risks, and requires explicit user confirmation before anything is downloaded or added to the skill library.
Defensive application-security auditing: turns a repo, manifest, or code snippet into an actionable report—dependency vulnerabilities, leaked secrets, insecure code patterns, and config hardening—mapped to OWASP Top 10 and ranked by severity. Finds risk and the fix only, never attack content.
Review your Merchant product CSV before submission. Get duplicate-ID, price/currency, required-field and supplied-GTIN checks, a row-linked HTML report, an editable fix queue and hashed evidence. Runs locally with Python; no paid API or account connection. Partial preflight, not Google approval.
Audits soccer analysis before conclusions are trusted: source tiers, dates and seasons, competition splits, 450-minute sample checks, availability flags, and uncertainty labels.
Catches cascade failures that partial checks miss — pre-check names the risk before editing, post-check demands evidence values after, then auto-repairs in a loop while rereading the entire file every cycle until zero errors remain.
Audit AI agents, Skills, MCP configurations, tool permissions, and coding-agent setups for prompt injection, excessive agency, credential exposure, data leakage, unsafe code execution, supply-chain risks, memory risks, missing approval controls, and runaway autonomy. Get a calibrated Security Score, Audit Confidence, evidence-backed findings, remediation steps, verification checks, and residual-risk analysis.
A senior-engineer-style code review assistant: severity-ranked findings, security smell detection, and constructive feedback across 8 language families.
Academic sanity-check with interactive HTML dashboard. Detects look-ahead bias, over-parameterization, and benchmarks against 10 canonical blueprints via animated SVG gauges and color-coded KPI cards. Parses natural language, code, or CSV uploads. Output auto-adapts (EN/ZH-TW/ZH-CN). Built on De Prado (2018). For students and strategy developers. Not financial advice.
Your AI built the app. Find out if it is ready to ship. Audits apps built with Cursor, Claude Code, Lovable, Bolt or v0 and ranks what will break after launch, worst first: auth holes, IDOR, Supabase RLS, exposed secrets (always masked), SQL/NoSQL/command injection, SSRF, XSS, payment webhooks and deploy blockers, plus SEO and AI-search readiness. Get a ship decision, scores, evidence-backed findings (file:line) and copy-paste fix prompts. Audit-only; your code is never executed.