forensic-qoe — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited forensic-qoe (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 deterministic OloLand tools for forensic checks. Do not infer forensic conclusions from prose alone — the verifier-stack premise is that every QoE conclusion comes from a tool with a documented methodology and inputs.
Each of these is available as an MCP tool / /-command in this plugin:
| Procedure | When required | Tool / command |
|---|---|---|
| Beneish M-Score | Every target. Earnings-manipulation probability. | /cmd-beneish |
| Benford distribution review | Whenever transaction-level GL data is available. Flags fabricated entries. | /cmd-benford |
| EBITDA bridge and adjustment quality | Every target. Walks from reported EBITDA to QoE-adjusted EBITDA with explicit adjustment categories. | /cmd-ebitda-bridge |
| Revenue quality deep dive | Whenever invoice-level or revenue-by-customer detail is available. | manual + tool stack |
| Working capital anomaly review | Every target. DSO/DIO/DPO trends + seasonality. | manual + tool stack |
| Journal entry testing | Whenever transaction-level data is available. Tests journal entries against fraud patterns (round numbers, period-end clustering, manual entries from privileged users). | /cmd-journal-test |
| Lapping detection | Whenever AR aging and cash receipts can be reconciled. | /cmd-lapping-check |
State the limitation explicitly. Do not fabricate a conclusion from incomplete data:
A QoE that skips a procedure because the data is missing is not a QoE failure — but the IC memo must surface the gap as a diligence condition.
For each procedure that ran:
For each procedure that did NOT run:
This output shape is what the /cmd-forensic-screen and /cmd-dd-analyze commands aggregate into a Pre-LOI Screen and full Forensic QoE respectively.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.