ha-quality-review

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill recommends several local shell commands for linting and validation, including ruff, mypy, grep, and python3. These are standard tools in a development environment and are used here to ensure code quality and schema compliance.\n- [EXTERNAL_DOWNLOADS]: Includes a reference to the official Home Assistant brands repository on GitHub (github.com/home-assistant/brands). This is a well-known service and the reference is documented neutrally for the purpose of integration branding compliance.\n- [PROMPT_INJECTION]: The skill operates on third-party integration code, which introduces an indirect prompt injection surface. This is inherent to its primary purpose as a code review tool.\n
  • Ingestion points: SKILL.md (Review Process) specifies the location of integration files to be analyzed.\n
  • Boundary markers: Absent; there are no specific delimiters to separate reviewed code from agent instructions.\n
  • Capability inventory: SKILL.md (Quick Validation Commands) identifies file-read and local command execution capabilities.\n
  • Sanitization: Absent; the skill does not explicitly sanitize the content of the integration files before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 05:46 AM
Security Audit — agent-trust-hub — ha-quality-review