Knowledge
Warn
Audited by Snyk on Aug 2, 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 the
/knowledge ingest <url-or-file>workflow, outsider-authored free text is ingested at runtime via WebFetch/curl of a user-supplied URL (or Read of a local file path) and then summarized/classified and used for ripple updates into the archive.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata