applications
Warn
Audited by Snyk on Feb 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly supports fetching job descriptions from arbitrary JD URLs via the "Via Claude skill" flow (and stores jd_url/jd_content from public job posting pages), so the agent will read and extract untrusted third-party web content that can influence later actions.
Audit Metadata