cx-metrics-query

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the cx CLI tool to search for metrics and execute PromQL queries. These commands are necessary for the skill's intended functionality and are used with standard arguments like --name and --time. \n- [PROMPT_INJECTION]: The skill processes untrusted data from metrics metadata and query results, representing an indirect prompt injection surface. \n
  • Ingestion points: Results from cx metrics search, cx metrics get-labels, and cx metrics query. \n
  • Boundary markers: No specific delimiters are used to wrap data from the CLI output. \n
  • Capability inventory: The agent has access to shell command execution through the cx CLI. \n
  • Sanitization: There are no explicit instructions to sanitize or validate strings returned from the metrics backend before processing them.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 05:40 AM