create-blog-post

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs cloning the public repository https://github.com/jim60105/blog.git and to read repository files (e.g., AGENTS.md and .github/instructions/quill-sage.instructions.md) so the agent will ingest and follow third-party repo content that can change its writing and actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill runtime instructs cloning the external repository https://github.com/jim60105/blog.git, and the fetched repo contains instruction files (e.g., .github/instructions/quill-sage.instructions.md, AGENTS.md, references/writing-guidelines.md) that directly control editorial prompts/instructions the agent must follow, so this external URL is a required runtime dependency that controls prompts.