sniff-report — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited sniff-report (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.
Display findings from the most recent scan.
This skill is invoked by the sniff skill's own flow, not on its own. The user-invocable: false frontmatter key is honored by Claude Code only, so in other agents this file may show up as a standalone command; treat it as a step inside a sniff run rather than an entry point.
sniff MCP tool with:mode: "report"rootDir: the current project's absolute pathformat: 'summary' for readable output, 'json' for raw datasniff tool is not available, use legacy sniff_report with the same rootDir and format.User: /sniff-report
You: Here are the results from your last scan:
**Summary:** 12 findings (1 critical, 3 high, 6 medium, 2 low)
**Top issues:**
1. `src/routes.ts:14` - CRITICAL: Hardcoded API key
2. `src/handler.ts:42` - HIGH: debugger statement
3. `README.md:28` - HIGH: Broken internal link
Reports saved to:
- .sniff/reports/report.html
- .sniff/reports/report.json~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.