query-logs
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses official Coralogix CLI tools, such as
cx logs,cx search-fields, andcx dataprime, to query and analyze log data. These tools are provided by the vendor and are used for their intended purpose within the skill. - [PROMPT_INJECTION]: The skill involves processing log data from external, potentially untrusted applications, which presents a surface for indirect prompt injection.
- Ingestion points: Data enters the agent's context through the output of
cx logsqueries and the inspection of log samples. - Boundary markers: There are no specific instructions regarding the use of boundary markers or delimiters to isolate untrusted log content from the agent's instructions.
- Capability inventory: The agent has access to Coralogix-specific tools for querying logs, searching fields, and interacting with other telemetry services.
- Sanitization: No mention of sanitizing or validating log content is made in the provided documentation.
Audit Metadata