actrun-init

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs fetching and running public third-party content (e.g., curl https://raw.githubusercontent.com/mizchi/actrun/main/install.sh and docker/ghcr.io pulls) and configures actrun to "trust_actions = true", meaning actrun will fetch and execute untrusted GitHub Actions from public repos as part of its workflow.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill's runtime installation steps fetch and execute remote code (e.g., curl -fsSL https://raw.githubusercontent.com/mizchi/actrun/main/install.sh | sh and git clone https://github.com/mizchi/actrun.git && moon build ...), so these external URLs are runtime dependencies that execute remote code.