create-midi
Warn
Audited by Snyk on Aug 26, 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). In the
composeruntime path,compose.pyreads user-provided--lyrics,--references,--arrangement, and--heartfree text from local files/CLI, embeds them into the LLM user message (_build_user_message), and sends that to the/prompt-lab-managed prompt via_call_scillm.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata