altinity-expert-clickhouse-reporting
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes query logs (
system.query_log) and process lists (system.processes) from ClickHouse. Since these logs contain raw query strings executed by users, they could potentially contain malicious instructions intended to influence the agent's behavior during analysis.\n - Ingestion points: SQL queries in
checks.sqlread fromsystem.query_log,system.processes, andsystem.query_views_log.\n - Boundary markers: None present in the SQL templates to distinguish between log data and instructions.\n
- Capability inventory: The skill facilitates read-only SELECT operations on system tables.\n
- Sanitization: No sanitization is performed on the query text retrieved from logs beyond truncation via
substring().\n- [SAFE]: The skill contains no executable code, remote downloads, or network exfiltration patterns. All operations are confined to diagnostic SQL queries within the ClickHouse environment. The vendor 'altinity' is the established provider for the technology being analyzed.
Audit Metadata