ha-api-access
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
curlcommands to interact with the Home Assistant REST API and usespython3(both thejson.toolmodule and inline scripts) to format and filter the results. - [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing external data from a Home Assistant instance.
- Ingestion points: Untrusted data enters the agent context through API responses from
$HA_URL/api/statesand$HA_URL/api/configwithinSKILL.md. - Boundary markers: There are no delimiters or instructions provided to the agent to treat the retrieved API data as non-executable content or to ignore potential instructions embedded within entity states.
- Capability inventory: The skill utilizes subprocess calls for
curlandpython3, providing a functional path for any injected instructions to trigger further commands. - Sanitization: No sanitization, validation, or escaping is applied to the values retrieved from the Home Assistant API before they are presented to the agent.
Audit Metadata