microsoft-edge-tts

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx node-edge-tts to download and execute the node-edge-tts package from the NPM registry. This is standard behavior for using this utility and occurs via a well-known service.\n- [COMMAND_EXECUTION]: The skill provides command-line examples for generating audio files and subtitles, involving shell execution of the downloaded package.\n- [PROMPT_INJECTION]: The skill processes user-supplied text for conversion to speech, which represents a data ingestion surface.\n
  • Ingestion points: Text input via the --text or -t parameter in the command examples.\n
  • Boundary markers: None; the instructions do not include delimiters or warnings for the agent to ignore instructions embedded in the provided text.\n
  • Capability inventory: The skill allows for command execution and local file writing.\n
  • Sanitization: None; the skill does not specify any methods for sanitizing or escaping the input text before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 04:17 AM
Security Audit — agent-trust-hub — microsoft-edge-tts