m3-graph — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited m3-graph (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 you want to visualize the connections, dependencies, contradictions, and references of a specific memory in the local Knowledge Graph.
Call m3:memory_graph with id="$ARGUMENTS", depth=2.
Render as an indented tree: the root memory at the top, each related memory underneath with the relationship type and direction (→ supersedes, ← derived_from, etc.). Truncate content to 80 chars per node.
If the result is empty, the memory has no recorded relationships yet. Suggest /m3:search for content-similar items instead.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.