altinity-expert-clickhouse-kafka
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- PROMPT_INJECTION (LOW): Indirect Prompt Injection surface detected. • Ingestion points: The skill reads from
system.text_loginchecks.sqland theexceptionscolumn ofsystem.kafka_consumersinadvanced_checks.sql, which store data that can be influenced by external actors (e.g., Kafka broker messages or errors). • Boundary markers: Absent; there are no specific delimiters or instructions for the agent to disregard commands embedded within the logs. • Capability inventory: The skill is limited to read-only SQL SELECT queries. It does not perform any file system modifications, network requests, or shell executions. • Sanitization: Absent; the skill retrieves and presents the log data in its raw, unprocessed form.
Audit Metadata