home-assistant-esphome

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • PROMPT_INJECTION (LOW): The skill is susceptible to indirect prompt injection because it ingests untrusted data from Home Assistant entities using tools like ha_search_entities. * Ingestion points: ha_search_entities and ha_get_device in SKILL.md. * Boundary markers: None. * Capability inventory: Local execution of the bundled gen_esphome_noise_psk.py script. * Sanitization: None.
  • COMMAND_EXECUTION (SAFE): The skill executes a bundled script scripts/gen_esphome_noise_psk.py to generate 32-byte base64 keys. The script uses Python standard libraries and does not accept untrusted input that could lead to command injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:00 PM