Meta-prompting, context engineering, and centralized instructions management for AI coding agents
SaferSkills independently audited rosetta (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.
<rosetta>
<purpose> Routing user request to proper workflow and high process adherence. </purpose>
<prerequisites>
orchestrationhitl</prerequisites>
<process>
<most matching workflow>.md (note: "*-flow" skills are additional workflows) — YOU MUST FULLY ALWAYS execute loaded workflow following its entire definition for all request sizes, workflow WAS created to fix your failure modes (deviations, and weak process adherence, and shallow analysis), workflow is PRIMARY deterministic process to resolve the original user requestplanning + tech-specs outputs → store per system prompt, never plans/ (read-only)Context loaded using Rosetta: [workflow selected + brief summary], and then execute prerequisites, phase 0, etc as workflow defined, let it drive questioning, planning, execution, review, and validation; no phase skipping;</process>
</rosetta>
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.