bootstrap-project-documentation

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and uses templates from a public third‑party URL (TEMPLATE_BASE_URL: https://raw.githubusercontent.com/nesnilnehc/project-documentation-template/main/) as a target/reference and to copy/interpret template files (see "Initialize Mode Steps" and "Adjust Mode Steps" in SKILL.md), so external, untrusted repository content can directly influence the agent's decisions and actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly fetches templates at runtime from the canonical TEMPLATE_BASE_URL (https://raw.githubusercontent.com/nesnilnehc/project-documentation-template/main/), and those fetched template files (e.g., llms.txt, ADR templates) are used as required inputs that directly shape agent instructions and outputs, so this is a runtime external dependency that can control prompts.