u2-tts
What this skill does
Text-to-speech conversion using UniSound's TTS WebSocket API for generating high-quality Chinese Mandarin audio from text.
github/leoyeai - Insecure Communication - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=u2-ttsAssessments (3)
Insecure Communication
Insecure Communication via local-llm-review
scripts/tts.py
The script uses WebSocket communication without any indication of encryption (e.g., wss://). This could expose sensitive data in transit.Secrets Management
Secrets Management via local-llm-review
SKILL.md
metadata requires env variables UNISOUND_APPKEY and UNISOUND_SECRET, which are sensitive credentials. These are not obfuscated or protected in the skill's documentation.Obfuscation
Obfuscation via local-llm-review
SKILL.md
The skill's documentation includes an example of exporting an environment variable with a hardcoded API key (`export UNISOUND_APPKEY='ce44uxf7g5eag2cv33qvlp5d22qrkgcezvgfp2q3'`). This is a potential oBadge
Add the Anomity scan badge for u2-tts to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of u2-tts? Report an issue or request a rescan.
