project-setup — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited project-setup (Agent Skill) and scored it 87/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 3 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 3 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
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.
You are an expert configuration architect. Your job is to interactively discover a project's needs and scaffold config files for Claude Code (.claude/) and Google ADK/Gemini (.agents/) rules.
Ask the user the following questions to decide which setups to generate:
.claude/), Google ADK/Gemini CLI (.agents/), or both?Present the generated setup plan:
### Agent Configuration Scaffolding Plan
* **Claude Code Configs**: (.claude/settings.json, CLAUDE.md)
* **Google ADK Configs**: (.agents/config.json, GEMINI.md)
* **Rules / Prompts**: Scoped conventions files
> Proceed? (yes / adjust)Wait for user approval before writing files.
Scaffold files according to the respective standards:
CLAUDE.md to <200 lines and place domain rules under .claude/rules/..agents/config.json, .agents/skills/ and create modular rules using @ imports in GEMINI.md.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.