botforge-93c0a2 — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited botforge-93c0a2 (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
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.
Load the canonical BotForge instructions from AGENTS.md. If the task needs the full skill workflow or detailed references, read .claude/skills/botforge/SKILL.md and only the specific reference file needed from .claude/skills/botforge/references/.
Use the six-stage workflow for new bots: Business brief, ADR, Project tree, Files, Self-review, Deployment. For small fixes, use the Bypass Protocol in AGENTS.md.
Hard bans remain active: no secrets in code, no blocking I/O or requests, no invented Telegram/aiogram APIs, no ORM outside repositories, no business logic in handlers, no unverified payments/webhooks, no dead Telegram UI.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.