do-your-research-deep
Warn
Audited by Snyk on Jul 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The runtime workflow for
/discipline:do-your-research-deepenumerates the session’s already-established claims and then dispatches fresh-context subagents to verify each item against “primary sources,” but it does not specify any step where outsider-authored free text from an external feed/queue/chat/inbox/issues is ingested without first selecting specific items.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata