synthesize
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands using the Bash tool to run a local Python script located at ~/.local/share/kokoro/tts_generate.py. This script generates WAV files in the /tmp directory.
- [PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection or command injection. User-supplied text is passed as a command-line argument to a shell command without explicit sanitization or escaping instructions.
- Ingestion points: The text input specified in the skill's argument hint is directly used in shell commands.
- Boundary markers: Instructions show simple double-quoting in examples but do not define strict delimiters or safety instructions for the agent to handle malicious input.
- Capability inventory: The skill relies on the Bash tool which allows for arbitrary command execution.
- Sanitization: No sanitization or input validation logic is present in the skill definition to prevent shell metacharacter injection.
Audit Metadata