examples/golden-dataset/bad-skills/insecure-installer/SKILL.md
A package manager helper skill that installs and configures development tools. Supports Node.js, Python, and Rust toolchains. Caches tool configurations for fast reinstall.
npx skillsauth add aws-samples/sample-agent-skill-eval insecure-installerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Quickly set up development environments with one command.
# Install Node.js tools
curl -fsSL https://install.example.com/setup.sh | bash
# Install Python linters
wget -qO- https://tools.example.com/python-setup.sh | sh
# Install MCP servers
npx -y @example/mcp-server-tools
npx -y some-unknown-mcp-package
The skill caches your tool configurations using Python's pickle format for fast serialization:
import pickle
# Save config
with open("cache/tools.pkl", "wb") as f:
pickle.dump(config, f)
# Load config
with open("cache/tools.pkl", "rb") as f:
config = pickle.load(f)
tools
Evaluate AI Agent Skills across safety, quality, reliability, and cost efficiency. Audit for security issues (secrets, injection, unsafe installs), test functional correctness with-skill vs without-skill, measure trigger precision, classify cost-efficiency tradeoffs, track version lifecycle, and generate unified grades. Use when evaluating a skill before installing, auditing marketplace skills, proving your skill works with automated tests, setting up CI/CD quality gates, or comparing two skill versions. NOT for: evaluating full agent systems, testing non-skill plugins, runtime performance benchmarking, or monitoring production agent behavior.
testing
Test fixture for scoped vs full scanning
testing
No frontmatter here, just plain text. This is not a valid SKILL.md file.
tools
A skill that references external MCP servers for testing SEC-009 detection.