ha-debugging
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains instructional content and standard development tools (ruff, mypy, python) used for debugging local Home Assistant code. No suspicious network activity or unauthorized data access was identified.
- [INDIRECT_PROMPT_INJECTION]: The skill includes instructions to read and validate local files such as
manifest.json,strings.json, and system logs. These files are typically under the control of the developer, but they represent a surface where untrusted data could enter the agent's context. - Ingestion points: Reads
manifest.json,strings.json, andhome-assistant.log(SKILL.md). - Boundary markers: None identified.
- Capability inventory: Executes shell commands including
python,ruff,mypy, andgrep(SKILL.md). - Sanitization: Standard validation is performed by the tools mentioned, but no specific agent-side sanitization of log content is described.
Audit Metadata