memory-protocol
Warn
Audited by Snyk on Sep 18, 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 queries a persistent knowledge graph via Memento MCP (
mcp__memento__semantic_searchandmcp__memento__open_nodes) to recall project history, errors, and cross-session learnings, which can contain user-submitted or outsider-authored content stored from previous interactions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata