Skills
skills/tul-sh/skills/text-to-speech/Gen Agent Trust Hub

text-to-speech

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the infsh CLI tool via the Bash(infsh *) allowed tool to perform tasks like model listing and speech generation.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface. 1. Ingestion points: The --input JSON parameter in infsh app run commands (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Shell command execution via Bash(infsh *) (SKILL.md). 4. Sanitization: Absent. User-provided text passed to external TTS models could contain malicious instructions designed to influence the model's output or the agent's logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 08:26 AM