oma-architecture

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the rg (ripgrep) command to search the local filesystem for files related to software architecture, such as ADRs and module boundaries. This is a standard, read-only operation appropriate for the skill's stated purpose.
  • [DATA_EXFILTRATION]: There are no network operations, API calls, or remote data transfer mechanisms. Outputs are restricted to the local directory .agents/results/architecture/.
  • [PROMPT_INJECTION]: The instructions focus purely on architectural methodologies (ATAM, CBAM, ADRs). No patterns suggesting safety bypasses, instruction overrides, or adversarial role-play were found.
  • [EXTERNAL_DOWNLOADS]: The skill does not fetch external code, scripts, or packages. All referenced resources are local markdown files within the skill package.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 12:18 PM
Security Audit — agent-trust-hub — oma-architecture