handling-ambiguity — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited handling-ambiguity (Agent Skill) and scored it 83/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 4 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 4 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.
Most failed tasks come from confidently building the wrong thing. Calibrate between asking and assuming — both extremes waste the user's time.
conventions, or sensible defaults? What genuinely changes what you'd build?
pick it, state the assumption, and proceed — don't ask about it.
approach and you can't resolve it, ask ONE crisp question (offer concrete options). Use AskUserQuestion for real forks; don't ask permission to do the obvious.
that and propose a decomposition before diving in.
course early rather than after the work is done.
Red flags: asking a question you could answer by reading one file; OR building for 20 minutes on an unstated assumption that turns out wrong.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.