openclaw-readonly-consumer — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited openclaw-readonly-consumer (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.
Use this skill when your local operator/runtime behaves like an OpenClaw-style shell and you want CampusCopilot to stay on the snapshot-first / thin-BFF-first / read-only side.
Think of CampusCopilot as the labeled binder on the desk:
pnpm --filter @campus-copilot/mcp-server startpnpm --filter @campus-copilot/mcp-readonly start:<site>pnpm start:apiexamples/workspace-snapshot.sample.jsonmcpServers JSON shape used by Codex/Claude-style MCP setupsexport CAMPUS_COPILOT_SNAPSHOT="$PWD/examples/workspace-snapshot.sample.json"mcpServers JSON shape, adapt:examples/integrations/codex-mcp.example.jsonexamples/integrations/claude-code-mcp.example.jsonexamples/openclaw-readonly.mdexamples/openclaw-readonly.mdexamples/README.mdskills/read-only-workspace-analysis/SKILL.mdskills/site-mcp-consumer/SKILL.md~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.