create-speech-recording-desktop

Pass

Audited by Gen Agent Trust Hub on Oct 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the agent-voice command-line interface to perform speech synthesis tasks.
  • Evidence: agent-voice speak "$RESPONSE_AS_TEXT" --wait in SKILL.md.
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to install and update the agent-voice tool from the author's public repository.
  • Evidence: uv tool install agent-voice and agent-voice update in SKILL.md.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes text from the agent's conversation history to generate audio, creating a potential surface for indirect prompt injection if the source text contains malicious instructions.
  • Ingestion points: The $RESPONSE_AS_TEXT variable in SKILL.md is populated from the agent's response context.
  • Boundary markers: The skill instructs the agent to wrap the variable in double quotes within the shell command.
  • Capability inventory: The skill has the ability to execute shell commands and write to the system temporary directory.
  • Sanitization: The instructions explicitly guide the agent to convert formatting characters (e.g., \n, \t) into plain-text spoken forms before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 17, 2026, 05:29 PM