profiling-statement-fingerprints
Warn
Audited by Snyk on Sep 14, 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 skill queries
crdb_internal.statement_statisticswhere query text and metadata from user SQL execution are stored as JSONB, representing outsider-authored free text ingested into the agent's runtime workflow via database queries.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata