forget — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited 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 /forget when the user says to forget, remove, delete, demote, or correct a stored memory.
Preview matching learnings:
lstack learn search "[query]" --json --limit 10Delete by id:
lstack learn forget --id 123Delete by exact key/type:
lstack learn forget --key auth-token-expiry --type pitfallDemote instead of deleting when the learning may still be useful locally but should not propagate:
lstack learn demote --id 123Preview:
lstack search "[query]"Delete after confirmation:
lstack forget "[query]"skill and explain that pruning/deleting the DB is a separate explicit action.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.