rpi — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited rpi (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.
Parse the first word of the input as the keyword (implement all [plan] / implement phase N [plan] is the shape there). plan, review, and implement accept a path to a .rpi/ document as context; implement with no path uses the most recent .rpi/plans/*.md (confirm with the user). Unknown or missing keyword → show the table and ask.
| Keyword | Reference | |
|---|---|---|
research <topic> | research — explore solutions with the user | |
| `plan <description \ | doc path>` | plan — TDD-structured implementation plan |
| `review <plan \ | artifact>` | review — findings list + verdict |
grill <topic> | grill — relentless interview until fully aligned | |
| `implement [all \ | phase N] [plan path]` | implement — orchestrate subagents through a plan's checklist |
handoff [focus] | handoff — summarize session for another agent | |
pickup [path] | pickup — resume from a handoff | |
write | write — save output to .rpi/ |
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.