building-dashboards

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides a suite of bash scripts (e.g., dashboard-create, dashboard-list, dashboard-update) that use curl, jq, and sed to interact with the Axiom API and manage local dashboard configurations.
  • [DATA_EXPOSURE]: Scripts are designed to read Axiom API tokens and organization IDs from the user's ~/.axiom.toml file. This is the documented and intended configuration mechanism for the tool to authenticate with the author's (Axiom) infrastructure.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes an attack surface where it ingests and processes user-provided dashboard JSON files and templates containing APL/MPL queries. It includes a dashboard-validate script to ensure structural integrity before deployment, which serves as a basic safeguard.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 07:24 AM
Security Audit — agent-trust-hub — building-dashboards