home-assistant-integration
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches markdown documentation and JSON configuration files from the official Home Assistant developers repository on GitHub (
https://raw.githubusercontent.com/home-assistant/developers.home-assistant/). - [COMMAND_EXECUTION]: The instructions direct the agent to execute local scripts from the user's repository, specifically
scripts/lintandscripts/test, to ensure code quality during the development process. - [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it ingests untrusted data from external documentation and local repository files to guide its actions.
- Ingestion points: Remote markdown and JSON files from GitHub, as well as local files such as
AGENTS.mdandpyproject.toml. - Boundary markers: The skill does not implement explicit delimiters or "ignore instructions" warnings for the content it fetches.
- Capability inventory: The agent can write files to the local filesystem and execute shell commands.
- Sanitization: No sanitization or validation of the fetched content is specified before it is processed by the agent.
Audit Metadata