knoxhub-blog
Warn
Audited by Snyk on Aug 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In
SKILL.mdStep 1, the workflow ingests user-provided raw article text/notes/topic and (when a URL is provided) fetches that URL viaWebFetchfor rewriting, so outsider-authored free text can be supplied directly by the caller and read/used by the LLM.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata