news-discover
Warn
Audited by Snyk on Feb 27, 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 workflow step 1 explicitly instructs the agent to "Search current news via web search for each active category", meaning the skill fetches and ingests open/public news websites (third‑party content) and the agent must read and act on that content to choose, prioritize, and follow up on stories, which could allow indirect prompt injection from untrusted sources.
Audit Metadata