cxas-autolabel-rules

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes uv run cxas to execute CLI commands for synchronizing local configurations with remote Google Cloud services. These commands include diff, pull, and push, which are standard operations for managing cloud resources.
  • [INDIRECT_PROMPT_INJECTION]: The skill translates natural language business requirements into Common Expression Language (CEL) boolean expressions. While this creates a processing surface for untrusted data, the resulting expressions are constrained by the CEL environment and the specific schema of CCAI Insights, which significantly limits the potential for exploitation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 02:19 PM
Security Audit — agent-trust-hub — cxas-autolabel-rules