tailor-resume

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly asks for and navigates to a user-supplied job URL and uses Claude-in-Chrome MCP browser automation to "navigate" and "get_page_text" (see SKILL.md Step 1 and the README's "fetches the job posting"), meaning it loads arbitrary public job postings (untrusted third‑party content) and directly reads/parses them to influence resume-generation 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 and injects the user-provided job posting URL (e.g., https://example.com/jobs/vp-growth) at runtime via browser automation (navigate + get_page_text) and uses that fetched page text to directly drive prompt content and resume generation, so the external URL controls agent instructions.