subscription-research-agent
Warn
Audited by Snyk on Jun 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The required runtime workflow for this skill (“subscription-research ingest rss” and optional “content fetch”) ingests outsider-authored free text from public RSS article pages (and their extracted full text) into the agent’s evidence brief context for synthesis.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata