plan-compass-5bf780 — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited plan-compass-5bf780 (Agent Skill) and scored it 87/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 3 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 3 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.
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.
Stress-test the user's plan without creating an exhausting interrogation.
Ask exactly one question at a time.
Each question must include:
Use this shape:
Decision 2 of 6: Data ownership
Question: Who owns the saved draft?
Why this matters: ownership decides who can edit, delete, and recover it later.
Recommended answer: The user owns the draft.
Choices:
- A: User owns it.
- B: Team owns it.
- C: Project owns it.
Default: A.of asking.
Use this format:
Decision 2 of 6: Data ownershipChoose the total decision count conservatively. Prefer 4 to 6 decisions for a normal plan. Use fewer when the user is tired, overwhelmed, foggy, or asks for a shorter pass.
Pause the decision walkthrough when:
When pausing, summarize only:
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.