narrative-review
Warn
Audited by Snyk on Jul 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The required workflow reads the user-supplied narrative file content from
--source-pathinto LLM-visible prose (Step 1/“Load Narrative”), and if that narrative is outsider-authored it would be treated as outsider free text injected via the file’s markdown body.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata