harvest-monitor
Warn
Audited by Snyk on Jun 22, 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 skill’s required workflow fetches arbitrary web page content at runtime from user-supplied URLs (e.g.,
https://docs.example.com/...) and then ingests that fetched free-form text into the LLM context for diffing/reporting, which is outsider-authored public web content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata