mem
Warn
Audited by Snyk on Sep 8, 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 agent skill provides workspace project snapshot building via
mem workspace build, which uses the authenticated Codex CLI to read active and archived rollouts underCODEX_HOMEcontaining user messages and task activity.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata