yb-query-analysis
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes database query logs and session history, which may contain strings influenced by external users or applications.
- Ingestion points: The agent is instructed to read and process data from
pg_stat_statements(both via SQL views and CSV exports) and theyb_active_session_historytable as part of the triage and analysis workflow described inSKILL.mdandreferences/triage-snapshot.sql. - Boundary markers: The skill does not provide specific instructions to the agent to wrap external content in delimiters or to ignore potential instructions embedded within the query text being analyzed.
- Capability inventory: The skill possesses capabilities for executing shell commands (
ysqlsh,kubectl,curl) and performing administrative database operations such as canceling transactions or modifying configuration settings. - Sanitization: There are no explicit instructions for filtering or sanitizing SQL query strings or session metadata before they are ingested into the agent's context for interpretation.
Audit Metadata