Chanjing Tts Voice Clone
Security checks across static analysis, malware telemetry, and agentic risk
Overview
The skill is coherent for Chanjing voice-clone TTS, but users should notice that it uses local Chanjing credentials, persists tokens, and sends voice/text data to Chanjing.
This appears safe for its stated purpose if you intend to use Chanjing's TTS service. Before installing, make sure you are comfortable storing Chanjing credentials in ~/.chanjing/credentials.json, submitting the reference-audio URL and text to Chanjing, and using only authorized voice material.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Using the skill lets it act through the user's Chanjing API account, and refreshed token material remains stored locally.
The skill reads Chanjing account credentials from a local credentials file and writes refreshed access-token fields back to disk.
CONFIG_FILE = CONFIG_DIR / "credentials.json" ... data["access_token"] = new_token ... data["expire_in"] = d.get("expire_in") ... write_config(data)Use only with a Chanjing account you intend to connect, keep credentials.json private, do not commit it to source control, and verify any CHANJING_API_BASE override before use.
Reference voice URLs and synthesis text may be processed by Chanjing, and generated audio may be available through provider-returned URLs.
The skill clearly discloses that user voice-reference data and generated output handling involve Chanjing's external service.
user-supplied public URL for reference audio (Chanjing servers fetch it); then synthesize and download from API-returned URLs
Only use audio and text you are allowed to submit to Chanjing, avoid sensitive material unless acceptable under the provider's terms, and ensure the reference URL is intentionally public.
A missing-credentials flow can execute the sibling login helper if it exists locally, so that helper's provenance matters too.
When credentials are missing, this skill may run a helper from a sibling skill rather than only files in its own manifest.
script = skills_dir / "chanjing-credentials-guard" / "scripts" / "open_login_page.py" ... subprocess.run([sys.executable, str(script)], check=False, timeout=5)
Install or keep the sibling credentials-guard skill only from a trusted source, or review that helper before relying on the automatic login-page flow.
