run-aql
Warn
Audited by Snyk on Nov 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow runs an agent-written AQL query via
execute_aqlagainst a user-specified Holistics dataset and reads the returned rows, which could include free-text columns that outsiders populated, but the agent must actively choose the query and the data is the user's own tenant rather than a monitored outsider-facing feed.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata