unity-gamedev-skill-pack

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly requires ingesting and interpreting content from external public repositories (e.g., the referenced GitHub repo https://github.com/tjboudreaux/cc-plugin-unity-gamedev) via "Step 1: Capture source provenance" and "Step 2: Extract reusable patterns", which can materially influence packaging and agent actions even though safety gates are mandated.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires retrieving external source URLs at runtime (e.g., https://github.com/tjboudreaux/cc-plugin-unity-gamedev) and uses fetched repository content to shape the agent's prompts/instructions during curation, so remote content can directly influence/ control agent behavior.