skills/deepgram/wsh/core/Gen Agent Trust Hub

core

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides documentation for the 'wsh' API, facilitating local terminal control via Unix domain sockets.
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection through terminal output ingestion. Ingestion points: Terminal screen and scrollback data endpoints (SKILL.md). Boundary markers: Absent. Capability inventory: Terminal input injection via API (SKILL.md). Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 12:49 AM
Security Audit — agent-trust-hub — core