maa-project-init
Warn
Audited by Snyk on Nov 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required file-scanning workflow reads only the user's own project files (interface.json, pipeline JSON, image inventory, agent Python via AST), with no outsider-authored free text; the only outsider-influenceable path is the optional live MaaMCP screencap/OCR step, where in-game text such as chat could in principle be authored by others, and the agent must actively choose to capture it.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata