claude-code-plugin/skills/ship-safe-baseline/SKILL.md
Manage your security baseline — accept current findings as known debt, then only report new regressions on future scans. Use when the user wants to adopt security scanning incrementally or suppress existing findings.
npx skillsauth add asamassekou10/ship-safe ship-safe-baselineInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You are helping the user manage their security baseline. A baseline lets teams "accept" current findings as known technical debt and only see new regressions on future scans.
--diff → Show what changed since the baseline was created--clear → Remove the baselinenpx ship-safe@latest baseline $ARGUMENTS 2>&1
If $ARGUMENTS is empty, default to .:
npx ship-safe@latest baseline . 2>&1
For diff mode:
npx ship-safe@latest baseline . --diff 2>&1
For clearing:
npx ship-safe@latest baseline --clear 2>&1
.ship-safe/baseline.json was creatednpx ship-safe audit . --baseline (or /ship-safe --baseline) to only see new findings.ship-safe/baseline.json to version control so the whole team shares the same baselineConfirm the baseline was removed. Future scans will show all findings again.
After creating a baseline, suggest this workflow:
npx ship-safe audit . --baseline --json to fail builds only on new findings/ship-safe-baseline --diff to track progress on reducing technical debt/ship-safe-baseline . to update the baselinerule:path:snippet), not line numbers — so the baseline survives code reformatting and line shiftstools
Run a full security audit on this project — 16 agents scan for secrets, injections, auth bypass, SSRF, supply chain, Supabase RLS, MCP security, agentic AI, RAG poisoning, PII compliance, and more. Use when the user wants a security audit, vulnerability scan, or asks if their code is safe to ship.
development
Get your project's security health score (0-100, A-F grade). Use when the user wants a quick security check or asks "is my code safe to ship?"
development
Quick scan for leaked secrets — API keys, passwords, tokens, database URLs. Use when the user wants to check for hardcoded secrets or exposed credentials.
tools
Run a multi-agent red team scan — 16 specialized security agents scan for 80+ attack classes including injection, auth bypass, SSRF, supply chain, Supabase RLS, MCP security, agentic AI, RAG poisoning, PII compliance, and more. Use when the user wants a deep security analysis beyond just secrets.