pre-commit

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and runs code from public, user-controlled repositories (e.g., .pre-commit-config.yaml entries and GitHub repo URLs in SKILL.md and HookGenerator, and runtime fetches via pre-commit in Tools/PreCommitManager.ts and Tools/HookValidator.ts which calls pre-commit try-repo), so untrusted third-party content is ingested and can change runtime behavior.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill includes CI workflow steps that fetch and execute remote code at runtime (e.g., curl -s https://raw.githubusercontent.com/terraform-linters/tflint/master/install_linux.sh | bash and downloads from https://releases.hashicorp.com/terraform/...), which clearly executes remote content during runtime and is a required dependency for those CI setups.