newscatcher
Warn
Audited by Snyk on Mar 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches public news article content from the NewsCatcher API (see SKILL.md entries like "Get Article Text", "Summarize Article", and the Membrane proxy request flow), so the agent ingests untrusted third‑party web content that could carry indirect prompt instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata