claude-mem
Warn
Audited by Snyk on May 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The make-plan.md Phase 0 "Documentation Discovery" and the subagent reporting contract explicitly require searching for and reading documentation/examples and returning "sources consulted (files/URLs)," which means the orchestrator flow will fetch and act on external (potentially public/untrusted) web or file content that can change planning and tool use.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata