personal-crm
Warn
Audited by Snyk on Aug 30, 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 instructs the model to pull recent meetings from meeting recorder MCP tools (such as Fireflies, Granola, Circleback, etc.) and ingest them into the vault, which introduces outsider-authored free text from meeting transcripts and recordings.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata