setup-devcontainer

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). High-risk: the skill instructs copying/mounting host credential files into the container and running remote install scripts (curl | bash), and optionally mounting the Docker socket — patterns that permit credential exposure, remote code execution and supply‑chain abuse.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill's entrypoint/installation guidance runs curl piped to bash at runtime to provision native CLIs (e.g., "curl -fsSL https://claude.ai/install.sh | bash" and "curl -fsSL https://cursor.com/install | bash"), which fetches and executes remote code that the setup relies on.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The prompt explicitly instructs the agent to mount and use the host Docker socket and to run docker-compose commands that can control host containers (equivalent to root on the host), which directly enables modification/compromise of the machine's state.