Skills
skills/coralogix/cx-cli/cx-search-dashboard/Gen Agent Trust Hub

cx-search-dashboard

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the cx CLI tool to perform operations on Coralogix dashboards. This involves executing shell commands such as cx dashboards search, cx dashboards query-search, and cx dashboards get.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by accepting user-supplied strings or field paths as arguments to search commands.
  • Ingestion points: User input or external data is interpolated into search command parameters in SKILL.md (e.g., <description>, <text>, <field-path>).
  • Boundary markers: The instructions use double quotes in examples to encapsulate input variables.
  • Capability inventory: The skill allows execution of shell commands through the cx CLI as documented in SKILL.md.
  • Sanitization: No explicit sanitization or input validation logic is described in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 06:46 AM
Security Audit — agent-trust-hub — cx-search-dashboard