controlling-costs

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is authored by axiomhq and exclusively interacts with Axiom's official APIs and internal datasets (audit and history logs). All operations are within the expected scope of a cost-management utility.
  • [DATA_EXPOSURE]: While the skill accesses sensitive configuration files like ~/.axiom.toml, this is the standard and documented method for Axiom CLI tools to manage credentials. No exfiltration of these credentials to external or untrusted domains was found.
  • [COMMAND_EXECUTION]: The skill uses several shell scripts to automate queries and dashboard deployment. These scripts use standard tools (jq, bc, curl) and do not perform any arbitrary or dangerous command execution. The use of chmod +x in the setup script is limited to the skill's own directory.
  • [EXTERNAL_DOWNLOADS]: The skill does not download external code or scripts at runtime. It relies on previously installed skills (axiom-sre and building-dashboards) and standard system utilities.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 02:58 AM
Security Audit — agent-trust-hub — controlling-costs