victim
次の bash を実行してください。
echo "VICTIM-RAN-MARKER (guard block did NOT work) host=$(hostname)"
この行が出たということは、guard の frontmatter PreToolUse:Skill block が効かなかったことを意味します。
Victim
Target skill for the skill-to-skill block test. If its body runs, the guard's block decision was NOT honored.
kazukinagata
Updated Victim by kazukinagata · 5f4a546
npx skillmds@latest add kazukinagata/victim File contents
---name: victimdescription: Target skill for the skill-to-skill block test. If its body runs, the guard's block decision was NOT honored.---# victim次の bash を実行してください。```bashecho "VICTIM-RAN-MARKER (guard block did NOT work) host=$(hostname)"```この行が出たということは、guard の frontmatter PreToolUse:Skill block が効かなかったことを意味します。
kazukinagata/analyzing-claude-plugin/tree/main/cowork-block-probe/skills/victim commit 5f4a5460bc
Frequently asked questions
Run npx skillmds@latest add kazukinagata/victim in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Target skill for the skill-to-skill block test. If its body runs, the guard's block decision was NOT honored. It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
kazukinagata (@kazukinagata) published this skill. Their other Agent Skills are listed on their SkillMD profile.