llm-wiki
Warn
Audited by Snyk on Jul 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The required runtime workflow for
ingest <SOURCE>reads the user-supplied source file (“Read the source file” and then “Read those pages in full” for synthesis), so if that file contains outsider-authored free text (e.g., downloaded/forwarded content), it will be ingested into the wiki and thus into the LLM context during subsequentquerysteps.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata