news
Warn
Audited by Snyk on Mar 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). Yes — the skill explicitly delegates to search-and-fetch to fetch and parse open/public third-party content (search queries and direct_sources such as Hacker News and GitHub Issues listed in config/sources.yaml and the fetch workflow in SKILL.md / references/fetch-strategy.md), and that untrusted content is read and integrated into the agent's outputs and decision flow, enabling potential indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata