extract-glossary

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

• Third-party content exposure detected (high risk: 0.90). This SKILL.md explicitly instructs the agent to read and extract content from GitHub URLs and repository files (e.g., "GitHub URL: https://github.com/org/repo" and the "2. コーパスを作る" section listing README/docs/schema/code), which are public, user-generated sources that the agent must interpret to drive its outputs, so untrusted third-party content could influence its actions.