create-speech-recording-controls

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the agent-voice CLI tool from the author's repository using the uv tool manager.
  • [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to store user-provided or user-influenced content in a variable that is subsequently executed in a shell command string (agent-voice speak "$RESPONSE_AS_TEXT"). This presents a command injection vulnerability if the input is not properly sanitized.
  • Ingestion points: User-supplied text, summaries, and table data provided in the skill instructions (SKILL.md).
  • Boundary markers: The instructions lack markers or specific directives to escape shell metacharacters.
  • Capability inventory: The skill leverages the agent-voice CLI tool to perform system-level actions.
  • Sanitization: No input validation or sanitization steps are defined for the handled text.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 09:13 AM
Security Audit — agent-trust-hub — create-speech-recording-controls