zod-nest-migrate

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to fetch and apply canonical step content from public GitHub URLs (e.g., "Fetch the section content (WebFetch the URL...)" in SKILL.md and the migration-steps references pointing to https://github.com/rodrigowbazevedo/zod-nest/blob/main/MIGRATION.md), so it will ingest and act on untrusted, user-controlled third-party content that can alter its actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly fetches the canonical migration sections at runtime from https://github.com/rodrigowbazevedo/zod-nest/blob/main/MIGRATION.md (and its anchor URLs) and uses that fetched content to drive prompts/instructions and apply code changes, so the external GitHub URL directly controls agent behavior.