memory-backup
Warn
Audited by Snyk on Jul 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). Restore/backup runtime path uses
gh repo view/git cloneto fetch an outsider-authored GitHub repository, then copies itsknowledge-base/*.mdandexperience/*.mdcontents into the local workspace (which are subsequently ingested by the agent/LLM via the knowledge base), creating an indirect prompt-injection channel from third-party text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata