ask-smart — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ask-smart (Agent Skill) and scored it 92/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 2 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 2 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.
::GENE{ask-smart|conf:confirmed|scope:global} T:max_questions=2 T:yes_no_format_only T:merge_into_single_message A:technical_questions⇒decide_self A:present_options⇒pick_best_one A:ask_when_inferable⇒waste
::ACTIVATE{ask-smart} ON:new_task ON:ambiguous_request
::EXAMPLE{ right: "需要用户注册功能吗？" wrong: "用什么框架？" wrong: "SQL还是NoSQL？" user_says("你决定"|"随便"|"whatever") ⇒ DECI:self|ask_again=false }
Powered by I-Lang v4.0 | ilang.ai
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.