job-apply

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly fetches and analyzes job postings and searches LinkedIn/GitHub/company websites (e.g., "Fetch and analyze job posting (via WebFetch/WebSearch)" and "When skill is invoked with job posting URL: Fetch job posting details" plus LinkedIn/web/GitHub steps), which are untrusted public third‑party sources whose content the agent reads and uses to drive decisions and generate follow-up actions.