ae-analysis-global

Pass

Audited by Gen Agent Trust Hub on Jul 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires the execution of the ae-cli command-line tool to verify the environment's multi-cluster configuration and to fetch inventory for available query clusters.
  • [PROMPT_INJECTION]: The skill processes data from external tool outputs (JSON DTOs) to determine logic flow and query routing, which represents a surface for indirect prompt injection.
  • Ingestion points: The skill ingests data from the output of ae-cli config cluster-mode status and ae-cli analysis +list_query_clusters (as defined in SKILL.md and references/list_query_clusters.md).
  • Boundary markers: No specific delimiters or boundary markers are used when the agent interprets this external data.
  • Capability inventory: The agent has the capability to execute shell commands using the ae-cli tool, including data retrieval and query execution.
  • Sanitization: The instructions do not define specific sanitization or validation logic for the tool's output, relying instead on provided permission flags (permissions.canQueryGlobal, etc.) to gate behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 26, 2026, 10:31 AM
Security Audit — agent-trust-hub — ae-analysis-global