echo-ingest-source-intake
Warn
Audited by Snyk on Jul 3, 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 runtime workflow explicitly supports ingesting “article/web pages” via current retrieval or “URL” sources, which are outsider-authored free text fetched at runtime and then normalized into Markdown for LLM context (step 4: “Normalize text into Markdown”).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata