constructive-boilerplate-pgpm-init

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

• Third-party content exposure detected (high risk: 0.90). The skill's "Custom Template Repositories" section (e.g., pgpm init --repo owner/repo or --repo https://github.com/owner/repo.git) and --boilerplate flow cause the CLI to fetch and ingest arbitrary public GitHub template repositories (untrusted, user-generated content) which are used to scaffold projects and can include scripts/workflows that materially influence subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The CLI fetches template repositories at runtime (e.g., constructive-io/pgpm-boilerplates and example form https://github.com/owner/repo.git or git@github.com:owner/repo.git via the --repo/--from-branch options), and those remote templates are cloned/used to generate scaffolding (thus directly controlling what is applied and potentially containing executable scripts), so this is a runtime external dependency that can control behavior.