database
Warn
Audited by Snyk on Aug 26, 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
databaseskill’s runtime workflow ingests SQL text supplied at call time (e.g.,database::query/database::execute“pass raw SQL only”), so an outsider who can provide that SQL can directly feed free text to the LLM/execution path.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata