sage-doctor
Warn
Audited by Snyk on Jul 24, 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). This workflow runs either
sage doctorfrom the current repo or falls back to executingnode "<SAGE_ROOT>/bin/sage" doctor, then feeds that command’s captured stdout (free-form text) verbatim into the agent’s conversation/context; this stdout is not clearly limited to trusted/bundled content and could include repo-authored text, which is effectively outsider-authored if the repo contents aren’t authored by the operating user.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata