mcp-engine-query — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited mcp-engine-query (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.
Query authoring and execution through run_query.
list_model { "operation": "list", "spec": { "type": "tables" } } — one call per type (tables, columns, measures, relationships; spec.type takes exactly one value) — or { "operation": "search", "spec": { "query": "<name>", "mode": "name" } } for a named object. Never invent table, column, or measure names.run_query operation:execute — results and validation queries.test_access — role-by-role RLS validation (requires top-level query and spec.roles).analyze and vertipaq belong to performance work — hand off to mcp-engine-dax-performance.execute scoped: TOPN of at most 100 rows with an explicit ORDER BY, or a targeted aggregation. Expand only after the shape is confirmed correct.null in results as DAX BLANK semantics, and truncated: true as a row cap, not missing data.ORDER BY to any multi-row output so results are stable and comparable across runs.After query work, report:
run_query operation used.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.