create-dashboard

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes untrusted data from repository files to build dashboards.
  • Ingestion points: Reads SKILL.md, source code files, and deployment configurations (meta.yaml, values.yaml) in Phase 1 to discover telemetry.
  • Boundary markers: The instructions do not include specific delimiters or warnings to ignore malicious instructions that might be embedded in these files.
  • Capability inventory: The skill performs extensive shell command execution through the 'cx' CLI and has file-write capabilities in the '/tmp/' directory.
  • Sanitization: Content extracted from local files is used without explicit validation or escaping before being incorporated into plans and queries.
  • [COMMAND_EXECUTION]: The skill relies on the 'cx' CLI to perform its primary functions, including telemetry discovery and dashboard deployment. This is documented and intended behavior for the Coralogix ecosystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 05:27 AM