bm-decide — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited bm-decide (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
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 when the user makes or asks to record a durable choice. A decision is a choice with rationale and consequences, not a casual preference.
.codex/basic-memory.json:primaryProject when setplacementConventions for the directory when they are specificdecisionsthe conversation already contains the rationale.
type: decision note:status: open unless the user says it is accepted, superseded, or rejecteddecided: <ISO timestamp when known>project: <primaryProject if known>note or link it as supersedes.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.