openclaw-voice-synthesis

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute standard macOS system utilities including 'say' for speech synthesis and 'afconvert' for audio format conversion.
  • [PROMPT_INJECTION]: The skill involves a surface for indirect prompt injection as it processes user-provided text within shell commands.
  • Ingestion points: Untrusted user input intended for conversion into audio artifacts (SKILL.md).
  • Boundary markers: No specific delimiters or safety warnings are provided to prevent the agent from interpreting instructions within the user text.
  • Capability inventory: Subprocess execution of the 'say' and 'afconvert' commands (SKILL.md).
  • Sanitization: There are no instructions for sanitizing, escaping, or validating the input text before it is used as a command-line argument.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 09:08 AM