claude-permissions
Warn
Audited by Snyk on Aug 9, 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). Outsider-authored free text is ingested only indirectly as the JSON hook payload (read from stdin) that can include tool input/commands; this content is passed to
dippyand its auto-mode[ASK]filtering without any prerequisite selection of a specific outsider text item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata