stitch-loop
Warn
Audited by Snyk on Aug 21, 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). The stitch-loop runtime workflow reads free-text prompt content from an outsider-modifiable baton file (
.stitch/next-prompt.md) and uses it directly in Stitch’sgenerate_screen_from_textcall, so an outsider who can write to that file can inject text into the agent.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata