syswatch-terminal-diagnostics

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to clone source code from an external repository located at https://github.com/matthart1983/syswatch.git. This repository is not maintained by a recognized trusted organization or the official vendor.
  • [COMMAND_EXECUTION]: Installation and operation require the execution of several shell commands, including git clone, cargo build, and binary execution. This involves running code compiled from an external source.
  • [PRIVILEGE_ESCALATION]: The documentation explicitly mentions that specific diagnostic features on macOS (such as per-component power and fan speeds via powermetrics) require sudo privileges, encouraging the use of elevated permissions for tool functionality.
  • [INDIRECT_PROMPT_INJECTION]: The tool ingests untrusted data from the local host that could contain malicious instructions designed to influence the agent's interpretation of system health.
  • Ingestion points: Data sources include process names (ps auxf), service lists (launchctl/systemctl), and filesystem labels which are read into the tool's diagnostic tabs.
  • Boundary markers: No boundary markers or "ignore instructions" warnings are present to separate system data from agent instructions.
  • Capability inventory: The skill has the capability to execute shell commands and read system-level telemetry across multiple subsystems.
  • Sanitization: The documentation does not describe any sanitization or filtering of the ingested telemetry data before it is presented in the TUI or processed for anomaly detection.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 10:36 AM