stitch-loop

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). At runtime the required workflow reads the baton file .stitch/next-prompt.md (Step 1) and injects its markdown body (which can contain arbitrary free text not authored by the operating user) into the LLM context via the Stitch MCP generate_screen_from_text prompt.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 24, 2026, 01:00 AM
Issues
1
Security Audit — snyk — stitch-loop