ololand-forensic-qoe-beneish — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ololand-forensic-qoe-beneish (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.
<!-- Generated by scripts/generate-plugin-artifacts.py; do not edit. -->
Follow the OloLand command instructions below when the user asks for /beneish or the equivalent workflow in Codex.
Compute the Beneish M-Score, an 8-variable model that estimates the probability of earnings manipulation. Originally designed for public companies; OloLand's implementation is private-company adjusted (handles missing market-cap inputs).
/beneish <deal_id>deal_id (required) — The deal whose financials to score. Requires at least two consecutive years of income statement + balance sheet data.run_beneish(deal_id) from the MCP server. Do not pass a primitives argument to analyze_forensic_qoe; that tool runs the full deal-scoped battery.The output includes each variable's value, the historical distribution for similar industries, and the marginal contribution to the score. If any single variable is the dominant driver of a high score, that variable points at the specific area of concern (e.g. SGI = revenue growth too fast vs. peers; AQI = aggressive capitalization).
The Beneish M-Score is the most widely-cited forensic accounting heuristic. Big-4 QoE engagements run it routinely. Surfacing it pre-LOI lets you decide whether to advance the deal before committing to a $250K Big-4 engagement.
/beneish deal_acme_2026~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.