skills/ingpoc/skills/speech/Gen Agent Trust Hub

speech

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were detected in the skill instructions or the bundled script.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the openai Python package, which is an official library from a well-known and trusted service provider.
  • [COMMAND_EXECUTION]: The skill uses a provided Python script (scripts/text_to_speech.py) to handle text-to-speech requests. The script is safely implemented using standard arguments and the official SDK, avoiding dangerous shell execution or subprocess calls.
  • [DATA_EXFILTRATION]: Text input is sent to the OpenAI API for synthesis. This is the intended functionality of the skill and uses official, well-known endpoints.
  • [CREDENTIALS_UNSAFE]: The skill manages API keys securely by directing the user to set them as environment variables and explicitly instructing the agent not to prompt for or share keys in the chat interface.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 09:45 AM
Security Audit — agent-trust-hub — speech