research
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 (medium risk: 0.65). The required workflow captures stdout from “research agents” into
research/raw/<thread>.mdand then the orchestrating agent assembles that verbatim outsider-authored free text intoresearch.md, which is later loaded by/design//plan//phase-planinto the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata