m3-forget — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited m3-forget (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 the user wants to delete a specific memory from their store. Always verify and confirm the deletion to prevent accidental loss of important information.
Step 1 — fetch the target via m3:memory_get with id="$ARGUMENTS". Show the user:
About to delete:
id: <uuid>
title: <title>
type: <type>
content: <first 200 chars>Step 2 — ask: "Type the first 8 chars of the id to confirm deletion, anything else to abort."
Step 3 — on match, call m3:memory_delete with the full id. On mismatch, abort and say "skipped — id mismatch."
If the user wants a softer alternative, mention m3:gdpr_forget (Article 17 — sets a tombstone instead of hard delete) or just writing a superseding memory via /m3:save.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.