v0.1.0 — Phylax public launch

First public release of Phylax — a pre-install security audit for agent skills on Base (chain 8453).

Phylax scans a skill before you install it and returns a deterministic ALLOW / WARN / DENY verdict with line-level evidence.

What it does

• Static scan — prompt-injection, secret-exfiltration, and obfuscation in SKILL.md + manifest
• Onchain scan — referenced Base contracts: bytecode selectors, proxy/upgradeability, honeypot/owner powers
• Endpoint scan — x402 endpoints: HTTPS enforcement, 402 schema, price sanity
• Deterministic scoring — score = 100 − Σ(severity_weight); same input → same verdict

Available everywhere

• npm: npm install phylax-skill-audit
• CLI: npx phylax --skill ./SKILL.md
• HTTP API: POST https://usephylax.com/api/audit (rate-limited, free)
• Aeon skill: ./add-skill aaronjmars/aeon phylax-audit — merged into Aeon

Verdict bands

Verdict	Condition
ALLOW	score ≥ 80, no critical/high
WARN	score 50–79, high but no critical
DENY	any critical, or score < 50

Notes

• 30+ open YAML rules across 6 categories (PI, SEC, CON, X402, MAN, LIQ)
• 30 tests passing; MIT licensed
• Honeypot simulation in deep mode is stubbed for this release (bytecode heuristics still run)
• x402 paid scans are planned, not yet shipped — the hosted API is currently free

Site: https://usephylax.com