altinity-expert-clickhouse-schema
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes metadata retrieved from ClickHouse system tables, which constitutes a vulnerability surface for indirect prompt injection if a malicious user can control database identifiers or comments.\n
- Ingestion points: Diagnostic query results from system.parts, system.tables, system.columns, and system.parts_columns as defined in the checks.sql file.\n
- Boundary markers: Absent. The instructions do not include delimiters or specific guidance for the agent to ignore potentially malicious instructions embedded within the query results.\n
- Capability inventory: No dangerous capabilities such as file system writing, network exfiltration, or subprocess execution are defined within the skill files.\n
- Sanitization: Absent. The results are processed by the agent without any prior validation, escaping, or filtering of the retrieved metadata.
Audit Metadata