← ClaudeAtlas

lint-baselinelisted

Audits a repository against the Adversis v0 security baseline for agentic SaaS applications. Produces a pass/gap/unknown verdict per baseline item plus framework-specific findings for FastAPI, Next.js, Supabase, and MCP server integration patterns. Use when you want to check an agentic app codebase before a security review.
Adversis/skills · ★ 0 · AI & Automation · score 58
Install: claude install-skill Adversis/skills
# lint-baseline v0 You are conducting a security audit of this codebase against the Adversis v0 baseline. The baseline is defined at `docs/v0-baseline.md` in this repo (or at adversis.io/baseline when published). ## Before you begin Ask: **"One-shot report or interactive walkthrough?"** - **One-shot**: run all checks, produce the full report, no questions - **Interactive**: work item by item; ask one targeted question before issuing a verdict on items with behavioral components (2, 4, 7, 8); allow discussion before moving to the next item Then proceed immediately to stack detection without waiting for further input. ## Step 1: Stack detection Read these files to identify which stack components are present: - `package.json` and/or `package-lock.json` - `requirements.txt`, `pyproject.toml`, or `uv.lock` - `docker-compose.yml` and/or `Dockerfile` - `.env.example` (if present) - Directory structure: presence of `app/`, `src/`, `pages/`, `app/` (Next.js app dir) Grep for these library patterns to confirm: - FastAPI: `from fastapi` or `fastapi` in requirements - SQLAlchemy: `sqlalchemy` in requirements - Next.js: `"next"` in package.json dependencies - Vercel AI SDK: `"ai"` in package.json dependencies - Supabase: `"@supabase/supabase-js"` in package.json - MCP servers: `mcp.json`, `.mcp.json`, `@modelcontextprotocol/sdk`, or `mcp` in requirements - Langfuse: `langfuse` in requirements or package.json - LangSmith: `langsmith` in requirements - Arize Phoenix: `arize-