resume-tailor

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

• Third-party content exposure detected (high risk: 1.00). This skill's STAGE 0 Job Description Input explicitly WebFetches arbitrary https:// URLs (open job postings) and the subagent ingests and analyzes that scraped JD content to extract requirements and drive tailoring decisions (keyword integration, ATS scoring, and draft generation), so untrusted third‑party content can directly influence agent behavior.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly WebFetches any user-provided URL (e.g., "https://...") at runtime to extract a job description and inject that content into the subagent/prompting pipeline to drive resume tailoring, meaning external content fetched at that URL can directly control prompts/outputs.