skills/aeondave/malskill/bluez/Gen Agent Trust Hub

bluez

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists of informational markdown files and does not include scripts, binaries, or automated code execution. All instructions involve standard Linux system utilities.
  • [INDIRECT_PROMPT_INJECTION]: The skill workflows involve reading untrusted data from Bluetooth devices. Ingestion points: Device names and attributes via bluetoothctl and btmon as described in references/scan-read-debug-workflow.md. Boundary markers: None identified in the provided instructions. Capability inventory: Uses system CLI tools (bluetoothctl, btmon, rfkill). Sanitization: None described for external device-provided strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 10:41 PM
Security Audit — agent-trust-hub — bluez