Skills/ClawHub/xiaozhi-teach-math-exam-designer

xiaozhi-teach-math-exam-designer@2.12.6

CAUTION

Publisher claims: "数学教师的测评设计（初中；高中含必修与选择性必修）：用双向细目表把"凭感觉出数学卷"变成可诊断的命题。仅在老师提出明确的数学命题任务时建议激活，例如"给八年级数学出一份期中试卷""算这次数学测评的逐题 P/D"；泛泛聊数学、问某题怎么解、问学生近况都不激活。只做四件事：命题蓝图与双向细目表、题目选编与版权标注、题目统计（逐题 P/D 与信度）、老师逐条确认后的写回。不做：错因归类与个体诊断（转 xiaozhi-teach-math-error-analyzer）、学员分层（转 xiaozhi-teach-student-analyzer）、补救与教学干预（转 xiaozhi-teach-math-lesson-planner）、家长版（学校班级转学情分析师，独立教师转家长沟通助手）、非数学学科测评（转 xiaozhi-teach-exam-designer）。" Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher qizhitang · joined 15 days agoInstalls 1,999Last detonated 1 h ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-06 and scored it 64/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: HTML comment carrying imperative instructions to the agent; HTML comment carrying imperative instructions to the agent; HTML comment carrying imperative instructions to the agent. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

CRITICAL
HTML comment carrying imperative instructions to the agentshared/grade-bands.md:1 · HTML comment carrying imperative instructions to the agentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentshared/crisis-exception.md:1 · HTML comment carrying imperative instructions to the agentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentshared/platform-conventions.md:1 · HTML comment carrying imperative instructions to the agentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentshared/crisis-referral-protocol.md:1 · HTML comment carrying imperative instructions to the agentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentshared/vocab.md:1 · HTML comment carrying imperative instructions to the agentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentshared/hint-ladder.md:1 · HTML comment carrying imperative instructions to the agentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentshared/ai-item-check.md:1 · HTML comment carrying imperative instructions to the agentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈5,787 tok
1 file · 18 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

16 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim qizhitang: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim qizhitangPropose a patch to the maintainer