manager-setup
Warn
Audited by Snyk on Aug 14, 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). Source:
Managerskill runtime—user-authored free text is ingested in the required workflow via$ARGUMENTS/natural-language prompt parsing for intent routing, and this text can directly drive actions likeinstall/enable/disable(which then alters the wall/codeword behavior), so the LLM sees outsider text before selecting a specific trusted item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata