Skills
Navigate
skills/altinity/altinity-skills/altinity-expert-clickhouse-mutations/Gen Agent Trust Hub

altinity-expert-clickhouse-mutations

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from ClickHouse system tables such as system.mutations and system.part_log where external strings (e.g., command text, error messages) could potentially influence agent behavior. 1. Ingestion points: Data enters the context via checks.sql queries against system.mutations and system.part_log. 2. Boundary markers: None explicitly defined in the skill instructions. 3. Capability inventory: SQL query execution on ClickHouse clusters. 4. Sanitization: None observed within the skill content.
  • [COMMAND_EXECUTION]: The skill documents administrative database commands like KILL MUTATION. These are provided as commented-out templates in SKILL.md for manual troubleshooting and are not set for automated execution by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 07:42 PM